{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2501.14249", "kind": "paper", "locator": "data/catalog/llm_stats_identity_overrides.yml#benchmarks.humanity's-last-exam.paper_url", "url": "https://arxiv.org/abs/2501.14249"}, {"id": "gh:centerforaisafety/hle", "kind": "repo", "locator": "data/catalog/llm_stats_identity_overrides.yml#benchmarks.humanity's-last-exam.repo_url", "url": "https://github.com/centerforaisafety/hle"}, {"id": "hf:cais/hle", "kind": "dataset", "locator": "data/catalog/llm_stats_identity_overrides.yml#benchmarks.humanity's-last-exam.dataset_url", "url": "https://huggingface.co/datasets/cais/hle"}], "categories": ["math", "reasoning", "vision"], "description": {"en": "Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions"}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "title": "Humanity's Last Exam"}], "evidence_summary": {"document_count": 1, "model_count": 99, "model_count_basis": "source_model_id"}, "identity_override": {"candidate_matches": [], "evidence": [{"anchor_type": "paper", "claim": "Official sources identify Center for AI Safety and Scale AI as collaborators. Dataset access requires sharing contact information.", "url": "https://arxiv.org/abs/2501.14249"}, {"anchor_type": "repo_readme", "claim": "Official sources identify Center for AI Safety and Scale AI as collaborators. Dataset access requires sharing contact information.", "url": "https://github.com/centerforaisafety/hle"}, {"anchor_type": "dataset_card", "claim": "Official sources identify Center for AI Safety and Scale AI as collaborators. Dataset access requires sharing contact information.", "url": "https://huggingface.co/datasets/cais/hle"}, {"anchor_type": "project_site", "claim": "Official sources identify Center for AI Safety and Scale AI as collaborators. Dataset access requires sharing contact information.", "url": "https://lastexam.ai/"}], "note": "Official sources identify Center for AI Safety and Scale AI as collaborators. Dataset access requires sharing contact information.", "repository": {"full_name": "centerforaisafety/hle", "kind": "benchmark_source", "resolution_status": "resolved", "subpath": null, "url": "https://github.com/centerforaisafety/hle"}, "resolution_status": "resolved", "source": "reviewed_llm_stats_identity_override", "source_path": "data/catalog/llm_stats_identity_overrides.yml"}, "key": "llm-stats:humanity's-last-exam", "modality": "multimodal", "name": "Humanity's Last Exam", "openness": {"access_gate": "reviewed_gate", "basis": "reviewed_data_gated", "code_license": "MIT", "code_license_note": null, "data_license": "MIT", "data_license_note": null, "data_located": "gated", "evidence": ["https://github.com/centerforaisafety/hle", "https://huggingface.co/datasets/cais/hle"], "link_status": null, "status": "restricted"}, "provenance": {"crawl_bundle": "llm_stats_2026-08-17", "crawled_at": "2026-08-17T18:49:35.489925+00:00", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500"}, "publisher": {"locator": "data/catalog/llm_stats_identity_overrides.yml#benchmarks.humanity's-last-exam.publisher", "name": "Center for AI Safety", "role": "paper_org"}, "released": "2025-01-24", "released_basis": "paper_first_version", "released_reference": null, "repository": {"full_name": "centerforaisafety/hle", "kind": "benchmark_source", "resolution_status": "resolved", "subpath": null, "url": "https://github.com/centerforaisafety/hle"}, "schema_version": 1, "sizes": [{"measures": "eval_set", "origin": "reviewed_llm_stats_identity_override", "split": "total", "unit": "questions", "value": 2500}], "slug": "llm-stats-humanity-s-last-exam", "source": "llm_stats", "source_benchmark_id": "humanity's-last-exam"}, "schema_version": 1, "scores_by_source": {"llm_stats": {"rows": [{"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-opus-5", "model_name": "Claude Opus 5", "obs_id": "llm_stats:humanity's-last-exam:claude-opus-5", "organization": "Anthropic", "rank_in_source_response": 1, "raw_value": "0.647", "reported_by": "self_reported", "reported_date": "2026-07-24", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.647, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-mythos-preview", "model_name": "Claude Mythos Preview", "obs_id": "llm_stats:humanity's-last-exam:claude-mythos-preview", "organization": "Anthropic", "rank_in_source_response": 2, "raw_value": "0.647", "reported_by": "self_reported", "reported_date": "2026-04-07", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.647, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-fable-5", "model_name": "Claude Fable 5", "obs_id": "llm_stats:humanity's-last-exam:claude-fable-5", "organization": "Anthropic", "rank_in_source_response": 3, "raw_value": "0.645", "reported_by": "self_reported", "reported_date": "2026-06-09", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.645, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-5.3", "model_name": "GLM-5.3", "obs_id": "llm_stats:humanity's-last-exam:glm-5.3", "organization": "Z.ai", "rank_in_source_response": 4, "raw_value": "0.625", "reported_by": "self_reported", "reported_date": "2026-08-14", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.625, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "muse-spark-1.1", "model_name": "Muse Spark 1.1", "obs_id": "llm_stats:humanity's-last-exam:muse-spark-1.1", "organization": "Meta", "rank_in_source_response": 5, "raw_value": "0.621", "reported_by": "self_reported", "reported_date": "2026-07-09", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.621, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v4-pro-0813", "model_name": "DeepSeek-V4-Pro-0813", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v4-pro-0813", "organization": "DeepSeek", "rank_in_source_response": 6, "raw_value": "0.6", "reported_by": "self_reported", "reported_date": "2026-08-13", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.6, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "muse-spark", "model_name": "Muse Spark", "obs_id": "llm_stats:humanity's-last-exam:muse-spark", "organization": "Meta", "rank_in_source_response": 7, "raw_value": "0.584", "reported_by": "self_reported", "reported_date": "2026-04-08", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.584, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-opus-4-8", "model_name": "Claude Opus 4.8", "obs_id": "llm_stats:humanity's-last-exam:claude-opus-4-8", "organization": "Anthropic", "rank_in_source_response": 8, "raw_value": "0.579", "reported_by": "self_reported", "reported_date": "2026-05-28", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.579, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-sonnet-5", "model_name": "Claude Sonnet 5", "obs_id": "llm_stats:humanity's-last-exam:claude-sonnet-5", "organization": "Anthropic", "rank_in_source_response": 9, "raw_value": "0.574", "reported_by": "self_reported", "reported_date": "2026-06-30", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.574, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "obs_id": "llm_stats:humanity's-last-exam:gpt-5.5-pro", "organization": "OpenAI", "rank_in_source_response": 10, "raw_value": "0.572", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.572, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "kimi-k3", "model_name": "Kimi K3", "obs_id": "llm_stats:humanity's-last-exam:kimi-k3", "organization": "Moonshot AI", "rank_in_source_response": 11, "raw_value": "0.56", "reported_by": "self_reported", "reported_date": "2026-07-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.56, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "seed-2.1-pro", "model_name": "Seed 2.1 Pro", "obs_id": "llm_stats:humanity's-last-exam:seed-2.1-pro", "organization": "ByteDance", "rank_in_source_response": 12, "raw_value": "0.557", "reported_by": "self_reported", "reported_date": "2026-06-24", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.557, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-5.2", "model_name": "GLM-5.2", "obs_id": "llm_stats:humanity's-last-exam:glm-5.2", "organization": "Z.ai", "rank_in_source_response": 13, "raw_value": "0.547", "reported_by": "self_reported", "reported_date": "2026-06-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.547, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-opus-4-7", "model_name": "Claude Opus 4.7", "obs_id": "llm_stats:humanity's-last-exam:claude-opus-4-7", "organization": "Anthropic", "rank_in_source_response": 14, "raw_value": "0.547", "reported_by": "self_reported", "reported_date": "2026-04-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.547, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "seed-2.1-turbo", "model_name": "Seed 2.1 Turbo", "obs_id": "llm_stats:humanity's-last-exam:seed-2.1-turbo", "organization": "ByteDance", "rank_in_source_response": 15, "raw_value": "0.546", "reported_by": "self_reported", "reported_date": "2026-06-24", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.546, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-opus-4-6", "model_name": "Claude Opus 4.6", "obs_id": "llm_stats:humanity's-last-exam:claude-opus-4-6", "organization": "Anthropic", "rank_in_source_response": 16, "raw_value": "0.531", "reported_by": "self_reported", "reported_date": "2026-02-05", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.531, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-5.1", "model_name": "GLM-5.1", "obs_id": "llm_stats:humanity's-last-exam:glm-5.1", "organization": "Z.ai", "rank_in_source_response": 17, "raw_value": "0.523", "reported_by": "self_reported", "reported_date": "2026-04-07", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.523, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5.5", "model_name": "GPT-5.5", "obs_id": "llm_stats:humanity's-last-exam:gpt-5.5", "organization": "OpenAI", "rank_in_source_response": 18, "raw_value": "0.522", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.522, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro", "obs_id": "llm_stats:humanity's-last-exam:gemini-3.1-pro-preview", "organization": "Google", "rank_in_source_response": 19, "raw_value": "0.514", "reported_by": "self_reported", "reported_date": "2026-02-19", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.514, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "kimi-k2-thinking-0905", "model_name": "Kimi K2-Thinking-0905", "obs_id": "llm_stats:humanity's-last-exam:kimi-k2-thinking-0905", "organization": "Moonshot AI", "rank_in_source_response": 20, "raw_value": "0.51", "reported_by": "self_reported", "reported_date": "2025-09-05", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.51, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "grok-4-heavy", "model_name": "Grok-4 Heavy", "obs_id": "llm_stats:humanity's-last-exam:grok-4-heavy", "organization": "xAI", "rank_in_source_response": 21, "raw_value": "0.507", "reported_by": "self_reported", "reported_date": "2025-07-09", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.507, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "kimi-k2.5", "model_name": "Kimi K2.5", "obs_id": "llm_stats:humanity's-last-exam:kimi-k2.5", "organization": "Moonshot AI", "rank_in_source_response": 22, "raw_value": "0.502", "reported_by": "self_reported", "reported_date": "2026-01-27", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.502, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "claude-sonnet-4-6", "model_name": "Claude Sonnet 4.6", "obs_id": "llm_stats:humanity's-last-exam:claude-sonnet-4-6", "organization": "Anthropic", "rank_in_source_response": 23, "raw_value": "0.49", "reported_by": "self_reported", "reported_date": "2026-02-17", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.49, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.5-27b", "model_name": "Qwen3.5-27B", "obs_id": "llm_stats:humanity's-last-exam:qwen3.5-27b", "organization": "Qwen", "rank_in_source_response": 24, "raw_value": "0.485", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.485, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v4-pro-max", "model_name": "DeepSeek-V4-Pro-Max", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v4-pro-max", "organization": "DeepSeek", "rank_in_source_response": 25, "raw_value": "0.482", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.482, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.5-122b-a10b", "model_name": "Qwen3.5-122B-A10B", "obs_id": "llm_stats:humanity's-last-exam:qwen3.5-122b-a10b", "organization": "Qwen", "rank_in_source_response": 26, "raw_value": "0.475", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.475, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.5-35b-a3b", "model_name": "Qwen3.5-35B-A3B", "obs_id": "llm_stats:humanity's-last-exam:qwen3.5-35b-a3b", "organization": "Qwen", "rank_in_source_response": 27, "raw_value": "0.474", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.474, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-3-pro-preview", "model_name": "Gemini 3 Pro", "obs_id": "llm_stats:humanity's-last-exam:gemini-3-pro-preview", "organization": "Google", "rank_in_source_response": 28, "raw_value": "0.458", "reported_by": "self_reported", "reported_date": "2025-11-18", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.458, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v4-flash-max", "model_name": "DeepSeek-V4-Flash-Max", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v4-flash-max", "organization": "DeepSeek", "rank_in_source_response": 29, "raw_value": "0.451", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.451, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.8-max", "model_name": "Qwen3.8 Max", "obs_id": "llm_stats:humanity's-last-exam:qwen3.8-max", "organization": "Qwen", "rank_in_source_response": 30, "raw_value": "0.436", "reported_by": "self_reported", "reported_date": "2026-08-02", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.436, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-3-flash-preview", "model_name": "Gemini 3 Flash", "obs_id": "llm_stats:humanity's-last-exam:gemini-3-flash-preview", "organization": "Google", "rank_in_source_response": 31, "raw_value": "0.435", "reported_by": "self_reported", "reported_date": "2025-12-17", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.435, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-4.7", "model_name": "GLM-4.7", "obs_id": "llm_stats:humanity's-last-exam:glm-4.7", "organization": "Z.ai", "rank_in_source_response": 32, "raw_value": "0.428", "reported_by": "self_reported", "reported_date": "2025-12-22", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.428, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.7-max", "model_name": "Qwen3.7 Max", "obs_id": "llm_stats:humanity's-last-exam:qwen3.7-max", "organization": "Qwen", "rank_in_source_response": 33, "raw_value": "0.414", "reported_by": "self_reported", "reported_date": "2026-05-19", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.414, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v3.2", "model_name": "DeepSeek-V3.2", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v3.2", "organization": "DeepSeek", "rank_in_source_response": 34, "raw_value": "0.408", "reported_by": "self_reported", "reported_date": "2025-12-01", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.408, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v4-flash-0423", "model_name": "DeepSeek-V4-Flash-0423", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v4-flash-0423", "organization": "DeepSeek", "rank_in_source_response": 35, "raw_value": "0.403", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.403, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "obs_id": "llm_stats:humanity's-last-exam:gemini-3.5-flash", "organization": "Google", "rank_in_source_response": 36, "raw_value": "0.402", "reported_by": "self_reported", "reported_date": "2026-05-19", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.402, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "grok-4", "model_name": "Grok-4", "obs_id": "llm_stats:humanity's-last-exam:grok-4", "organization": "xAI", "rank_in_source_response": 37, "raw_value": "0.4", "reported_by": "self_reported", "reported_date": "2025-07-09", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.4, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5.4", "model_name": "GPT-5.4", "obs_id": "llm_stats:humanity's-last-exam:gpt-5.4", "organization": "OpenAI", "rank_in_source_response": 38, "raw_value": "0.398", "reported_by": "self_reported", "reported_date": "2026-03-05", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.398, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "ernie-5.0", "model_name": "ERNIE 5.0", "obs_id": "llm_stats:humanity's-last-exam:ernie-5.0", "organization": "Baidu", "rank_in_source_response": 39, "raw_value": "0.39", "reported_by": "self_reported", "reported_date": "2026-01-22", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.39, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra (550B A55B)", "obs_id": "llm_stats:humanity's-last-exam:nemotron-3-ultra-550b-a55b", "organization": "NVIDIA", "rank_in_source_response": 40, "raw_value": "0.374", "reported_by": "self_reported", "reported_date": "2026-06-04", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.374, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5.2-pro-2025-12-11", "model_name": "GPT-5.2 Pro", "obs_id": "llm_stats:humanity's-last-exam:gpt-5.2-pro-2025-12-11", "organization": "OpenAI", "rank_in_source_response": 41, "raw_value": "0.366", "reported_by": "self_reported", "reported_date": "2025-12-11", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.366, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "kimi-k2.6", "model_name": "Kimi K2.6", "obs_id": "llm_stats:humanity's-last-exam:kimi-k2.6", "organization": "Moonshot AI", "rank_in_source_response": 42, "raw_value": "0.364", "reported_by": "self_reported", "reported_date": "2026-04-20", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.364, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.7-plus", "model_name": "Qwen3.7-Plus", "obs_id": "llm_stats:humanity's-last-exam:qwen3.7-plus", "organization": "Qwen", "rank_in_source_response": 43, "raw_value": "0.347", "reported_by": "self_reported", "reported_date": "2026-05-31", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.347, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5.2-2025-12-11", "model_name": "GPT-5.2", "obs_id": "llm_stats:humanity's-last-exam:gpt-5.2-2025-12-11", "organization": "OpenAI", "rank_in_source_response": 44, "raw_value": "0.345", "reported_by": "self_reported", "reported_date": "2025-12-11", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.345, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "mimo-v2.5-pro", "model_name": "MiMo-V2.5-Pro", "obs_id": "llm_stats:humanity's-last-exam:mimo-v2.5-pro", "organization": "Xiaomi", "rank_in_source_response": 45, "raw_value": "0.34", "reported_by": "self_reported", "reported_date": "2026-04-27", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.34, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "inkling-small", "model_name": "Inkling-Small", "obs_id": "llm_stats:humanity's-last-exam:inkling-small", "organization": "Thinking Machines Lab", "rank_in_source_response": 46, "raw_value": "0.316", "reported_by": "self_reported", "reported_date": "2026-07-30", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.316, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.8-27b", "model_name": "Qwen3.8-27B", "obs_id": "llm_stats:humanity's-last-exam:qwen3.8-27b", "organization": "Qwen", "rank_in_source_response": 47, "raw_value": "0.308", "reported_by": "self_reported", "reported_date": "2026-08-14", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.308, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v3.2-speciale", "model_name": "DeepSeek-V3.2-Speciale", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v3.2-speciale", "organization": "DeepSeek", "rank_in_source_response": 48, "raw_value": "0.306", "reported_by": "self_reported", "reported_date": "2025-12-01", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.306, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.6-plus", "model_name": "Qwen3.6 Plus", "obs_id": "llm_stats:humanity's-last-exam:qwen3.6-plus", "organization": "Qwen", "rank_in_source_response": 49, "raw_value": "0.288", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.288, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.5-397b-a17b", "model_name": "Qwen3.5-397B-A17B", "obs_id": "llm_stats:humanity's-last-exam:qwen3.5-397b-a17b", "organization": "Qwen", "rank_in_source_response": 50, "raw_value": "0.287", "reported_by": "self_reported", "reported_date": "2026-02-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.287, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5.4-mini", "model_name": "GPT-5.4 mini", "obs_id": "llm_stats:humanity's-last-exam:gpt-5.4-mini", "organization": "OpenAI", "rank_in_source_response": 51, "raw_value": "0.282", "reported_by": "self_reported", "reported_date": "2026-03-17", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.282, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemma-4-31b-it", "model_name": "Gemma 4 31B", "obs_id": "llm_stats:humanity's-last-exam:gemma-4-31b-it", "organization": "Google", "rank_in_source_response": 52, "raw_value": "0.265", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.265, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "longcat-flash-thinking-2601", "model_name": "LongCat-Flash-Thinking-2601", "obs_id": "llm_stats:humanity's-last-exam:longcat-flash-thinking-2601", "organization": "Meituan", "rank_in_source_response": 53, "raw_value": "0.252", "reported_by": "self_reported", "reported_date": "2026-01-14", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.252, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-reasoner", "model_name": "DeepSeek-V3.2 (Thinking)", "obs_id": "llm_stats:humanity's-last-exam:deepseek-reasoner", "organization": "DeepSeek", "rank_in_source_response": 54, "raw_value": "0.251", "reported_by": "self_reported", "reported_date": "2025-12-01", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.251, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5-2025-08-07", "model_name": "GPT-5", "obs_id": "llm_stats:humanity's-last-exam:gpt-5-2025-08-07", "organization": "OpenAI", "rank_in_source_response": 55, "raw_value": "0.248", "reported_by": "self_reported", "reported_date": "2025-08-07", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.248, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5.4-nano", "model_name": "GPT-5.4 nano", "obs_id": "llm_stats:humanity's-last-exam:gpt-5.4-nano", "organization": "OpenAI", "rank_in_source_response": 56, "raw_value": "0.243", "reported_by": "self_reported", "reported_date": "2026-03-17", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.243, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.6-27b", "model_name": "Qwen3.6-27B", "obs_id": "llm_stats:humanity's-last-exam:qwen3.6-27b", "organization": "Qwen", "rank_in_source_response": 57, "raw_value": "0.24", "reported_by": "self_reported", "reported_date": "2026-04-21", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.24, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "nemotron-3-super-120b-a12b", "model_name": "Nemotron 3 Super (120B A12B)", "obs_id": "llm_stats:humanity's-last-exam:nemotron-3-super-120b-a12b", "organization": "NVIDIA", "rank_in_source_response": 58, "raw_value": "0.2282", "reported_by": "self_reported", "reported_date": "2026-03-11", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.2282, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "mimo-v2-flash", "model_name": "MiMo-V2-Flash", "obs_id": "llm_stats:humanity's-last-exam:mimo-v2-flash", "organization": "Xiaomi", "rank_in_source_response": 59, "raw_value": "0.221", "reported_by": "self_reported", "reported_date": "2025-12-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.221, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "muse-glimmer-30b", "model_name": "Muse Glimmer-30B", "obs_id": "llm_stats:humanity's-last-exam:muse-glimmer-30b", "organization": "Meta", "rank_in_source_response": 60, "raw_value": "0.22", "reported_by": "self_reported", "reported_date": "2026-08-10", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.22, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "minimax-m2.1", "model_name": "MiniMax M2.1", "obs_id": "llm_stats:humanity's-last-exam:minimax-m2.1", "organization": "MiniMax", "rank_in_source_response": 61, "raw_value": "0.22", "reported_by": "self_reported", "reported_date": "2025-12-23", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.22, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-2.5-pro-preview-06-05", "model_name": "Gemini 2.5 Pro Preview 06-05", "obs_id": "llm_stats:humanity's-last-exam:gemini-2.5-pro-preview-06-05", "organization": "Google", "rank_in_source_response": 62, "raw_value": "0.216", "reported_by": "self_reported", "reported_date": "2025-06-05", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.216, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3.6-35b-a3b", "model_name": "Qwen3.6-35B-A3B", "obs_id": "llm_stats:humanity's-last-exam:qwen3.6-35b-a3b", "organization": "Qwen", "rank_in_source_response": 63, "raw_value": "0.214", "reported_by": "self_reported", "reported_date": "2026-04-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.214, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "grok-4-fast", "model_name": "Grok 4 Fast", "obs_id": "llm_stats:humanity's-last-exam:grok-4-fast", "organization": "xAI", "rank_in_source_response": 64, "raw_value": "0.2", "reported_by": "self_reported", "reported_date": "2025-08-28", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.2, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v3.2-exp", "model_name": "DeepSeek-V3.2-Exp", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v3.2-exp", "organization": "DeepSeek", "rank_in_source_response": 65, "raw_value": "0.198", "reported_by": "self_reported", "reported_date": "2025-09-29", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.198, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3-235b-a22b-thinking-2507", "model_name": "Qwen3-235B-A22B-Thinking-2507", "obs_id": "llm_stats:humanity's-last-exam:qwen3-235b-a22b-thinking-2507", "organization": "Qwen", "rank_in_source_response": 66, "raw_value": "0.182", "reported_by": "self_reported", "reported_date": "2025-07-25", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.182, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "mai-code-1-flash", "model_name": "MAI-Code-1-Flash", "obs_id": "llm_stats:humanity's-last-exam:mai-code-1-flash", "organization": "Microsoft", "rank_in_source_response": 67, "raw_value": "0.18", "reported_by": "self_reported", "reported_date": "2026-06-02", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.18, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "obs_id": "llm_stats:humanity's-last-exam:gemini-2.5-pro", "organization": "Google", "rank_in_source_response": 68, "raw_value": "0.178", "reported_by": "self_reported", "reported_date": "2025-05-20", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.178, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-r1-0528", "model_name": "DeepSeek-R1-0528", "obs_id": "llm_stats:humanity's-last-exam:deepseek-r1-0528", "organization": "DeepSeek", "rank_in_source_response": 69, "raw_value": "0.177", "reported_by": "self_reported", "reported_date": "2025-05-28", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.177, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemma-4-26b-a4b-it", "model_name": "Gemma 4 26B-A4B", "obs_id": "llm_stats:humanity's-last-exam:gemma-4-26b-a4b-it", "organization": "Google", "rank_in_source_response": 70, "raw_value": "0.172", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.172, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-4.6", "model_name": "GLM-4.6", "obs_id": "llm_stats:humanity's-last-exam:glm-4.6", "organization": "Z.ai", "rank_in_source_response": 71, "raw_value": "0.172", "reported_by": "self_reported", "reported_date": "2025-09-30", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.172, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5-mini-2025-08-07", "model_name": "GPT-5 mini", "obs_id": "llm_stats:humanity's-last-exam:gpt-5-mini-2025-08-07", "organization": "OpenAI", "rank_in_source_response": 72, "raw_value": "0.167", "reported_by": "self_reported", "reported_date": "2025-08-07", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.167, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-3.1-flash-lite-preview", "model_name": "Gemini 3.1 Flash-Lite", "obs_id": "llm_stats:humanity's-last-exam:gemini-3.1-flash-lite-preview", "organization": "Google", "rank_in_source_response": 73, "raw_value": "0.16", "reported_by": "self_reported", "reported_date": "2026-03-03", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.16, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "deepseek-v3.1", "model_name": "DeepSeek-V3.1", "obs_id": "llm_stats:humanity's-last-exam:deepseek-v3.1", "organization": "DeepSeek", "rank_in_source_response": 74, "raw_value": "0.159", "reported_by": "self_reported", "reported_date": "2025-01-10", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.159, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "nemotron-3-nano-30b-a3b", "model_name": "Nemotron 3 Nano (30B A3B)", "obs_id": "llm_stats:humanity's-last-exam:nemotron-3-nano-30b-a3b", "organization": "NVIDIA", "rank_in_source_response": 75, "raw_value": "0.155", "reported_by": "self_reported", "reported_date": "2025-12-15", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.155, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-oss-120b", "model_name": "GPT OSS 120B", "obs_id": "llm_stats:humanity's-last-exam:gpt-oss-120b", "organization": "OpenAI", "rank_in_source_response": 76, "raw_value": "0.149", "reported_by": "self_reported", "reported_date": "2025-08-05", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.149, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "o4-mini", "model_name": "o4-mini", "obs_id": "llm_stats:humanity's-last-exam:o4-mini", "organization": "OpenAI", "rank_in_source_response": 77, "raw_value": "0.147", "reported_by": "self_reported", "reported_date": "2025-04-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.147, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "o3-2025-04-16", "model_name": "o3", "obs_id": "llm_stats:humanity's-last-exam:o3-2025-04-16", "organization": "OpenAI", "rank_in_source_response": 78, "raw_value": "0.147", "reported_by": "self_reported", "reported_date": "2025-04-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.147, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-4.7-flash", "model_name": "GLM-4.7-Flash", "obs_id": "llm_stats:humanity's-last-exam:glm-4.7-flash", "organization": "Z.ai", "rank_in_source_response": 79, "raw_value": "0.144", "reported_by": "self_reported", "reported_date": "2026-01-19", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.144, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-4.5", "model_name": "GLM-4.5", "obs_id": "llm_stats:humanity's-last-exam:glm-4.5", "organization": "Z.ai", "rank_in_source_response": 80, "raw_value": "0.144", "reported_by": "self_reported", "reported_date": "2025-07-28", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.144, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 VL 235B A22B Thinking", "obs_id": "llm_stats:humanity's-last-exam:qwen3-vl-235b-a22b-thinking", "organization": "Qwen", "rank_in_source_response": 81, "raw_value": "0.136", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.136, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "minimax-m2", "model_name": "MiniMax M2", "obs_id": "llm_stats:humanity's-last-exam:minimax-m2", "organization": "MiniMax", "rank_in_source_response": 82, "raw_value": "0.125", "reported_by": "self_reported", "reported_date": "2025-10-27", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.125, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "diffusiongemma-26b-a4b-it", "model_name": "DiffusionGemma 26B-A4B", "obs_id": "llm_stats:humanity's-last-exam:diffusiongemma-26b-a4b-it", "organization": "Google", "rank_in_source_response": 83, "raw_value": "0.119", "reported_by": "self_reported", "reported_date": "2026-06-10", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.119, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "nemotron-3.5-lightning-30b-a3b", "model_name": "Nemotron 3.5 Lightning (30B A3B)", "obs_id": "llm_stats:humanity's-last-exam:nemotron-3.5-lightning-30b-a3b", "organization": "NVIDIA", "rank_in_source_response": 84, "raw_value": "0.1172", "reported_by": "self_reported", "reported_date": "2026-08-11", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.1172, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "sarvam-105b", "model_name": "Sarvam-105B", "obs_id": "llm_stats:humanity's-last-exam:sarvam-105b", "organization": "Sarvam AI", "rank_in_source_response": 85, "raw_value": "0.112", "reported_by": "self_reported", "reported_date": "2026-03-06", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.112, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "obs_id": "llm_stats:humanity's-last-exam:gemini-2.5-flash", "organization": "Google", "rank_in_source_response": 86, "raw_value": "0.11", "reported_by": "self_reported", "reported_date": "2025-05-20", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.11, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-oss-20b", "model_name": "GPT OSS 20B", "obs_id": "llm_stats:humanity's-last-exam:gpt-oss-20b", "organization": "OpenAI", "rank_in_source_response": 87, "raw_value": "0.109", "reported_by": "self_reported", "reported_date": "2025-08-05", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.109, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "glm-4.5-air", "model_name": "GLM-4.5-Air", "obs_id": "llm_stats:humanity's-last-exam:glm-4.5-air", "organization": "Z.ai", "rank_in_source_response": 88, "raw_value": "0.106", "reported_by": "self_reported", "reported_date": "2025-07-28", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.106, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "magistral-medium", "model_name": "Magistral Medium", "obs_id": "llm_stats:humanity's-last-exam:magistral-medium", "organization": "Mistral", "rank_in_source_response": 89, "raw_value": "0.09", "reported_by": "self_reported", "reported_date": "2025-06-10", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.09, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-5-nano-2025-08-07", "model_name": "GPT-5 nano", "obs_id": "llm_stats:humanity's-last-exam:gpt-5-nano-2025-08-07", "organization": "OpenAI", "rank_in_source_response": 90, "raw_value": "0.087", "reported_by": "self_reported", "reported_date": "2025-08-07", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.087, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "minimax-m1-80k", "model_name": "MiniMax M1 80K", "obs_id": "llm_stats:humanity's-last-exam:minimax-m1-80k", "organization": "MiniMax", "rank_in_source_response": 91, "raw_value": "0.084", "reported_by": "self_reported", "reported_date": "2025-06-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.084, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "minimax-m1-40k", "model_name": "MiniMax M1 40K", "obs_id": "llm_stats:humanity's-last-exam:minimax-m1-40k", "organization": "MiniMax", "rank_in_source_response": 92, "raw_value": "0.072", "reported_by": "self_reported", "reported_date": "2025-06-16", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.072, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-4.1-2025-04-14", "model_name": "GPT-4.1", "obs_id": "llm_stats:humanity's-last-exam:gpt-4.1-2025-04-14", "organization": "OpenAI", "rank_in_source_response": 93, "raw_value": "0.054", "reported_by": "self_reported", "reported_date": "2025-04-14", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.054, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-4o-2024-08-06", "model_name": "GPT-4o", "obs_id": "llm_stats:humanity's-last-exam:gpt-4o-2024-08-06", "organization": "OpenAI", "rank_in_source_response": 94, "raw_value": "0.053", "reported_by": "self_reported", "reported_date": "2024-08-06", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.053, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemma-4-12b-it", "model_name": "Gemma 4 12B", "obs_id": "llm_stats:humanity's-last-exam:gemma-4-12b-it", "organization": "Google", "rank_in_source_response": 95, "raw_value": "0.052", "reported_by": "self_reported", "reported_date": "2026-05-23", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.052, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash-Lite", "obs_id": "llm_stats:humanity's-last-exam:gemini-2.5-flash-lite", "organization": "Google", "rank_in_source_response": 96, "raw_value": "0.051", "reported_by": "self_reported", "reported_date": "2025-06-17", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.051, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "kimi-k2-instruct-0905", "model_name": "Kimi K2-Instruct-0905", "obs_id": "llm_stats:humanity's-last-exam:kimi-k2-instruct-0905", "organization": "Moonshot AI", "rank_in_source_response": 97, "raw_value": "0.047", "reported_by": "self_reported", "reported_date": "2025-09-05", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.047, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "kimi-k2-instruct", "model_name": "Kimi K2 Instruct", "obs_id": "llm_stats:humanity's-last-exam:kimi-k2-instruct", "organization": "Moonshot AI", "rank_in_source_response": 98, "raw_value": "0.047", "reported_by": "self_reported", "reported_date": "2025-07-11", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.047, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "key": "llm-stats:humanity's-last-exam", "measured_by": null, "model_id": "gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini", "obs_id": "llm_stats:humanity's-last-exam:gpt-4.1-mini-2025-04-14", "organization": "OpenAI", "rank_in_source_response": 99, "raw_value": "0.037", "reported_by": "self_reported", "reported_date": "2025-04-14", "series_id": "llm_stats:humanity's-last-exam:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500", "value": 0.037, "value_kind": "number"}], "series": {"bounds": {"basis": "aggregator_declared", "max": 1.0, "min": null}, "declared_max": 1.0, "direction": "higher_is_better", "direction_basis": "source_rank_descending", "display_scale": null, "first_score_record": {"date_precision": "model_announcement", "obs_id": "llm_stats:humanity's-last-exam:gpt-4o-2024-08-06", "reported_at": "2024-08-06", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500"}, "first_score_report": null, "key": "llm-stats:humanity's-last-exam", "max_score_contradicted": false, "metric": null, "observation_count": 99, "observed_max": 0.647, "score_summary": {"display_max": 64.7, "display_multiplier": 100, "model_count": 99, "model_count_basis": "source_model_id", "numeric_count": 99, "raw_max": 0.647, "raw_min": 0.037, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:humanity's-last-exam:claude-mythos-preview", "reported_date": "2026-04-07", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/humanity%27s-last-exam?top_n=500"}, "unit": null}, "series_id": "llm_stats:humanity's-last-exam:default"}}}, "siblings": []}
