{"record": {"aliases": [], "artifacts": [{"id": "gh:harbor-framework/terminal-bench-2", "kind": "repo", "locator": "data/catalog/llm_stats_identity_overrides.yml#benchmarks.terminal-bench-2.repo_url", "url": "https://github.com/harbor-framework/terminal-bench-2"}], "categories": ["reasoning", "agents", "code", "tool_calling"], "description": {"en": "Terminal-Bench 2.0 is an updated benchmark for testing AI agents' tool use ability to operate a computer via terminal. It evaluates how well models can handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, security tasks, data science workflows, and cybersecurity vulnerabilities."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "title": "Terminal-Bench 2.0"}], "evidence_summary": {"document_count": 1, "model_count": 51, "model_count_basis": "source_model_id"}, "identity_override": {"candidate_matches": [], "evidence": [{"anchor_type": "repo_readme", "claim": "Official site and version-specific repository agree. Task data are embedded in the repository, not a separate dataset page.", "url": "https://github.com/harbor-framework/terminal-bench-2"}, {"anchor_type": "project_site", "claim": "Official site and version-specific repository agree. Task data are embedded in the repository, not a separate dataset page.", "url": "https://www.tbench.ai/benchmarks/terminal-bench-2"}], "note": "Official site and version-specific repository agree. Task data are embedded in the repository, not a separate dataset page.", "repository": {"full_name": "harbor-framework/terminal-bench-2", "kind": "benchmark_source", "resolution_status": "resolved", "subpath": null, "url": "https://github.com/harbor-framework/terminal-bench-2"}, "resolution_status": "resolved", "source": "reviewed_llm_stats_identity_override", "source_path": "data/catalog/llm_stats_identity_overrides.yml"}, "key": "llm-stats:terminal-bench-2", "modality": "text", "name": "Terminal-Bench 2.0", "openness": {"access_gate": null, "basis": "reviewed_data_found_without_license", "code_license": "Apache-2.0", "code_license_note": null, "data_license": null, "data_license_note": null, "data_located": "found", "evidence": ["https://github.com/harbor-framework/terminal-bench-2"], "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/terminal-bench-2?top_n=500"}, "publisher": null, "released": "2025-09-25", "released_basis": "repo_created", "released_reference": null, "repository": {"full_name": "harbor-framework/terminal-bench-2", "kind": "benchmark_source", "resolution_status": "resolved", "subpath": null, "url": "https://github.com/harbor-framework/terminal-bench-2"}, "schema_version": 1, "sizes": [{"measures": "eval_set", "origin": "reviewed_llm_stats_identity_override", "split": "total", "unit": "tasks", "value": 89}], "slug": "llm-stats-terminal-bench-2", "source": "llm_stats", "source_benchmark_id": "terminal-bench-2"}, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gpt-5.5", "model_name": "GPT-5.5", "obs_id": "llm_stats:terminal-bench-2:gpt-5.5", "organization": "OpenAI", "rank_in_source_response": 1, "raw_value": "0.827", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.827, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "claude-mythos-preview", "model_name": "Claude Mythos Preview", "obs_id": "llm_stats:terminal-bench-2:claude-mythos-preview", "organization": "Anthropic", "rank_in_source_response": 2, "raw_value": "0.82", "reported_by": "self_reported", "reported_date": "2026-04-07", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.82, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "claude-sonnet-5", "model_name": "Claude Sonnet 5", "obs_id": "llm_stats:terminal-bench-2:claude-sonnet-5", "organization": "Anthropic", "rank_in_source_response": 3, "raw_value": "0.804", "reported_by": "self_reported", "reported_date": "2026-06-30", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.804, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "obs_id": "llm_stats:terminal-bench-2:gpt-5.3-codex", "organization": "OpenAI", "rank_in_source_response": 4, "raw_value": "0.773", "reported_by": "self_reported", "reported_date": "2026-02-05", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.773, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "obs_id": "llm_stats:terminal-bench-2:gemini-3.5-flash", "organization": "Google", "rank_in_source_response": 5, "raw_value": "0.762", "reported_by": "self_reported", "reported_date": "2026-05-19", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.762, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gpt-5.4", "model_name": "GPT-5.4", "obs_id": "llm_stats:terminal-bench-2:gpt-5.4", "organization": "OpenAI", "rank_in_source_response": 6, "raw_value": "0.751", "reported_by": "self_reported", "reported_date": "2026-03-05", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.751, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "claude-opus-4-8", "model_name": "Claude Opus 4.8", "obs_id": "llm_stats:terminal-bench-2:claude-opus-4-8", "organization": "Anthropic", "rank_in_source_response": 7, "raw_value": "0.746", "reported_by": "self_reported", "reported_date": "2026-05-28", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.746, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.7-plus", "model_name": "Qwen3.7-Plus", "obs_id": "llm_stats:terminal-bench-2:qwen3.7-plus", "organization": "Qwen", "rank_in_source_response": 8, "raw_value": "0.703", "reported_by": "self_reported", "reported_date": "2026-05-31", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.703, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.7-max", "model_name": "Qwen3.7 Max", "obs_id": "llm_stats:terminal-bench-2:qwen3.7-max", "organization": "Qwen", "rank_in_source_response": 9, "raw_value": "0.697", "reported_by": "self_reported", "reported_date": "2026-05-19", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.697, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "claude-opus-4-7", "model_name": "Claude Opus 4.7", "obs_id": "llm_stats:terminal-bench-2:claude-opus-4-7", "organization": "Anthropic", "rank_in_source_response": 10, "raw_value": "0.694", "reported_by": "self_reported", "reported_date": "2026-04-16", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.694, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "glm-5.1", "model_name": "GLM-5.1", "obs_id": "llm_stats:terminal-bench-2:glm-5.1", "organization": "Z.ai", "rank_in_source_response": 11, "raw_value": "0.69", "reported_by": "self_reported", "reported_date": "2026-04-07", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.69, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro", "obs_id": "llm_stats:terminal-bench-2:gemini-3.1-pro-preview", "organization": "Google", "rank_in_source_response": 12, "raw_value": "0.685", "reported_by": "self_reported", "reported_date": "2026-02-19", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.685, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "mimo-v2.5-pro", "model_name": "MiMo-V2.5-Pro", "obs_id": "llm_stats:terminal-bench-2:mimo-v2.5-pro", "organization": "Xiaomi", "rank_in_source_response": 13, "raw_value": "0.684", "reported_by": "self_reported", "reported_date": "2026-04-27", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.684, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "deepseek-v4-pro-max", "model_name": "DeepSeek-V4-Pro-Max", "obs_id": "llm_stats:terminal-bench-2:deepseek-v4-pro-max", "organization": "DeepSeek", "rank_in_source_response": 14, "raw_value": "0.679", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.679, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "kimi-k2.6", "model_name": "Kimi K2.6", "obs_id": "llm_stats:terminal-bench-2:kimi-k2.6", "organization": "Moonshot AI", "rank_in_source_response": 15, "raw_value": "0.667", "reported_by": "self_reported", "reported_date": "2026-04-20", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.667, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "mimo-v2.5", "model_name": "MiMo-V2.5", "obs_id": "llm_stats:terminal-bench-2:mimo-v2.5", "organization": "Xiaomi", "rank_in_source_response": 16, "raw_value": "0.658", "reported_by": "self_reported", "reported_date": "2026-04-22", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.658, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "claude-opus-4-6", "model_name": "Claude Opus 4.6", "obs_id": "llm_stats:terminal-bench-2:claude-opus-4-6", "organization": "Anthropic", "rank_in_source_response": 17, "raw_value": "0.654", "reported_by": "self_reported", "reported_date": "2026-02-05", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.654, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "obs_id": "llm_stats:terminal-bench-2:gpt-5.2-codex", "organization": "OpenAI", "rank_in_source_response": 18, "raw_value": "0.64", "reported_by": "self_reported", "reported_date": "2026-01-14", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.64, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.6-plus", "model_name": "Qwen3.6 Plus", "obs_id": "llm_stats:terminal-bench-2:qwen3.6-plus", "organization": "Qwen", "rank_in_source_response": 19, "raw_value": "0.616", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.616, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gpt-5.4-mini", "model_name": "GPT-5.4 mini", "obs_id": "llm_stats:terminal-bench-2:gpt-5.4-mini", "organization": "OpenAI", "rank_in_source_response": 20, "raw_value": "0.6", "reported_by": "self_reported", "reported_date": "2026-03-17", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.6-27b", "model_name": "Qwen3.6-27B", "obs_id": "llm_stats:terminal-bench-2:qwen3.6-27b", "organization": "Qwen", "rank_in_source_response": 21, "raw_value": "0.593", "reported_by": "self_reported", "reported_date": "2026-04-21", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.593, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "claude-opus-4-5-20251101", "model_name": "Claude Opus 4.5", "obs_id": "llm_stats:terminal-bench-2:claude-opus-4-5-20251101", "organization": "Anthropic", "rank_in_source_response": 22, "raw_value": "0.593", "reported_by": "self_reported", "reported_date": "2025-11-24", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.593, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "claude-sonnet-4-6", "model_name": "Claude Sonnet 4.6", "obs_id": "llm_stats:terminal-bench-2:claude-sonnet-4-6", "organization": "Anthropic", "rank_in_source_response": 23, "raw_value": "0.591", "reported_by": "self_reported", "reported_date": "2026-02-17", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.591, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "muse-spark", "model_name": "Muse Spark", "obs_id": "llm_stats:terminal-bench-2:muse-spark", "organization": "Meta", "rank_in_source_response": 24, "raw_value": "0.59", "reported_by": "self_reported", "reported_date": "2026-04-08", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.59, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "mimo-v2-pro", "model_name": "MiMo-V2-Pro", "obs_id": "llm_stats:terminal-bench-2:mimo-v2-pro", "organization": "Xiaomi", "rank_in_source_response": 25, "raw_value": "0.571", "reported_by": "self_reported", "reported_date": "2026-03-18", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.571, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "minimax-m2.7", "model_name": "MiniMax M2.7", "obs_id": "llm_stats:terminal-bench-2:minimax-m2.7", "organization": "MiniMax", "rank_in_source_response": 26, "raw_value": "0.57", "reported_by": "self_reported", "reported_date": "2026-03-18", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.57, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "deepseek-v4-flash-max", "model_name": "DeepSeek-V4-Flash-Max", "obs_id": "llm_stats:terminal-bench-2:deepseek-v4-flash-max", "organization": "DeepSeek", "rank_in_source_response": 27, "raw_value": "0.569", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.569, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "deepseek-v4-flash-0423", "model_name": "DeepSeek-V4-Flash-0423", "obs_id": "llm_stats:terminal-bench-2:deepseek-v4-flash-0423", "organization": "DeepSeek", "rank_in_source_response": 28, "raw_value": "0.566", "reported_by": "self_reported", "reported_date": "2026-04-23", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.566, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "glm-5", "model_name": "GLM-5", "obs_id": "llm_stats:terminal-bench-2:glm-5", "organization": "Z.ai", "rank_in_source_response": 29, "raw_value": "0.562", "reported_by": "self_reported", "reported_date": "2026-02-11", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.562, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "mai-code-1-flash", "model_name": "MAI-Code-1-Flash", "obs_id": "llm_stats:terminal-bench-2:mai-code-1-flash", "organization": "Microsoft", "rank_in_source_response": 30, "raw_value": "0.548", "reported_by": "self_reported", "reported_date": "2026-06-02", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.548, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gemini-3-pro-preview", "model_name": "Gemini 3 Pro", "obs_id": "llm_stats:terminal-bench-2:gemini-3-pro-preview", "organization": "Google", "rank_in_source_response": 31, "raw_value": "0.542", "reported_by": "self_reported", "reported_date": "2025-11-18", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.542, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "obs_id": "llm_stats:terminal-bench-2:gpt-5.1-codex", "organization": "OpenAI", "rank_in_source_response": 32, "raw_value": "0.528", "reported_by": "self_reported", "reported_date": "2025-11-19", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.528, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.5-397b-a17b", "model_name": "Qwen3.5-397B-A17B", "obs_id": "llm_stats:terminal-bench-2:qwen3.5-397b-a17b", "organization": "Qwen", "rank_in_source_response": 33, "raw_value": "0.525", "reported_by": "self_reported", "reported_date": "2026-02-16", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.525, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.6-35b-a3b", "model_name": "Qwen3.6-35B-A3B", "obs_id": "llm_stats:terminal-bench-2:qwen3.6-35b-a3b", "organization": "Qwen", "rank_in_source_response": 34, "raw_value": "0.515", "reported_by": "self_reported", "reported_date": "2026-04-16", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.515, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "step-3.5-flash", "model_name": "Step-3.5-Flash", "obs_id": "llm_stats:terminal-bench-2:step-3.5-flash", "organization": "StepFun", "rank_in_source_response": 35, "raw_value": "0.51", "reported_by": "self_reported", "reported_date": "2026-02-02", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "kimi-k2.5", "model_name": "Kimi K2.5", "obs_id": "llm_stats:terminal-bench-2:kimi-k2.5", "organization": "Moonshot AI", "rank_in_source_response": 36, "raw_value": "0.508", "reported_by": "self_reported", "reported_date": "2026-01-27", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.508, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.5-122b-a10b", "model_name": "Qwen3.5-122B-A10B", "obs_id": "llm_stats:terminal-bench-2:qwen3.5-122b-a10b", "organization": "Qwen", "rank_in_source_response": 37, "raw_value": "0.494", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.494, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gemini-3-flash-preview", "model_name": "Gemini 3 Flash", "obs_id": "llm_stats:terminal-bench-2:gemini-3-flash-preview", "organization": "Google", "rank_in_source_response": 38, "raw_value": "0.476", "reported_by": "self_reported", "reported_date": "2025-12-17", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.476, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "deepseek-v3.2", "model_name": "DeepSeek-V3.2", "obs_id": "llm_stats:terminal-bench-2:deepseek-v3.2", "organization": "DeepSeek", "rank_in_source_response": 39, "raw_value": "0.464", "reported_by": "self_reported", "reported_date": "2025-12-01", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.464, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "deepseek-reasoner", "model_name": "DeepSeek-V3.2 (Thinking)", "obs_id": "llm_stats:terminal-bench-2:deepseek-reasoner", "organization": "DeepSeek", "rank_in_source_response": 40, "raw_value": "0.464", "reported_by": "self_reported", "reported_date": "2025-12-01", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.464, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "deepseek-v3.2-speciale", "model_name": "DeepSeek-V3.2-Speciale", "obs_id": "llm_stats:terminal-bench-2:deepseek-v3.2-speciale", "organization": "DeepSeek", "rank_in_source_response": 41, "raw_value": "0.464", "reported_by": "self_reported", "reported_date": "2025-12-01", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.464, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "gpt-5.4-nano", "model_name": "GPT-5.4 nano", "obs_id": "llm_stats:terminal-bench-2:gpt-5.4-nano", "organization": "OpenAI", "rank_in_source_response": 42, "raw_value": "0.463", "reported_by": "self_reported", "reported_date": "2026-03-17", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.463, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "mai-thinking-1", "model_name": "MAI-Thinking-1", "obs_id": "llm_stats:terminal-bench-2:mai-thinking-1", "organization": "Microsoft", "rank_in_source_response": 43, "raw_value": "0.46", "reported_by": "self_reported", "reported_date": "2026-06-02", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.46, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.5-27b", "model_name": "Qwen3.5-27B", "obs_id": "llm_stats:terminal-bench-2:qwen3.5-27b", "organization": "Qwen", "rank_in_source_response": 44, "raw_value": "0.416", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.416, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "glm-4.7", "model_name": "GLM-4.7", "obs_id": "llm_stats:terminal-bench-2:glm-4.7", "organization": "Z.ai", "rank_in_source_response": 45, "raw_value": "0.41", "reported_by": "self_reported", "reported_date": "2025-12-22", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.41, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3.5-35b-a3b", "model_name": "Qwen3.5-35B-A3B", "obs_id": "llm_stats:terminal-bench-2:qwen3.5-35b-a3b", "organization": "Qwen", "rank_in_source_response": 46, "raw_value": "0.405", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.405, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "mimo-v2-flash", "model_name": "MiMo-V2-Flash", "obs_id": "llm_stats:terminal-bench-2:mimo-v2-flash", "organization": "Xiaomi", "rank_in_source_response": 47, "raw_value": "0.385", "reported_by": "self_reported", "reported_date": "2025-12-16", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.385, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "laguna-xs-2.1", "model_name": "Laguna XS 2.1", "obs_id": "llm_stats:terminal-bench-2:laguna-xs-2.1", "organization": "Poolside", "rank_in_source_response": 48, "raw_value": "0.375", "reported_by": "self_reported", "reported_date": "2026-07-02", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.375, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "qwen3-coder-480b-a35b-instruct", "model_name": "Qwen3-Coder 480B A35B Instruct", "obs_id": "llm_stats:terminal-bench-2:qwen3-coder-480b-a35b-instruct", "organization": "Qwen", "rank_in_source_response": 49, "raw_value": "0.375", "reported_by": "self_reported", "reported_date": "2025-01-31", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.375, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "north-mini-code-1.0", "model_name": "North Mini Code 1.0", "obs_id": "llm_stats:terminal-bench-2:north-mini-code-1.0", "organization": "Cohere", "rank_in_source_response": 50, "raw_value": "0.36", "reported_by": "self_reported", "reported_date": "2026-06-09", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.36, "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/terminal-bench-2?top_n=500", "key": "llm-stats:terminal-bench-2", "measured_by": null, "model_id": "nemotron-3-super-120b-a12b", "model_name": "Nemotron 3 Super (120B A12B)", "obs_id": "llm_stats:terminal-bench-2:nemotron-3-super-120b-a12b", "organization": "NVIDIA", "rank_in_source_response": 51, "raw_value": "0.31", "reported_by": "self_reported", "reported_date": "2026-03-11", "series_id": "llm_stats:terminal-bench-2:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500", "value": 0.31, "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:terminal-bench-2:qwen3-coder-480b-a35b-instruct", "reported_at": "2025-01-31", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500"}, "first_score_report": null, "key": "llm-stats:terminal-bench-2", "max_score_contradicted": false, "metric": null, "observation_count": 51, "observed_max": 0.827, "score_summary": {"display_max": 82.69999999999999, "display_multiplier": 100, "model_count": 51, "model_count_basis": "source_model_id", "numeric_count": 51, "raw_max": 0.827, "raw_min": 0.31, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:terminal-bench-2:gpt-5.5", "reported_date": "2026-04-23", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/terminal-bench-2?top_n=500"}, "unit": null}, "series_id": "llm_stats:terminal-bench-2:default"}}}, "siblings": []}
