{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2403.07974", "kind": "paper", "locator": "data/catalog/llm_stats_identity_overrides.yml#benchmarks.livecodebench-v6.paper_url", "url": "https://arxiv.org/abs/2403.07974"}, {"id": "gh:LiveCodeBench/LiveCodeBench", "kind": "repo", "locator": "data/catalog/llm_stats_identity_overrides.yml#benchmarks.livecodebench-v6.repo_url", "url": "https://github.com/LiveCodeBench/LiveCodeBench"}], "categories": ["reasoning", "general"], "description": {"en": "LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "title": "LiveCodeBench v6"}], "evidence_summary": {"document_count": 1, "model_count": 56, "model_count_basis": "source_model_id"}, "identity_override": {"candidate_matches": [], "evidence": [{"anchor_type": "paper", "claim": "The official repository documents release_v6, and the paper introduces the same contamination-free code benchmark.", "url": "https://arxiv.org/abs/2403.07974"}, {"anchor_type": "repo_readme", "claim": "The official repository documents release_v6, and the paper introduces the same contamination-free code benchmark.", "url": "https://github.com/LiveCodeBench/LiveCodeBench"}], "note": "The official repository documents release_v6, and the paper introduces the same contamination-free code benchmark.", "repository": {"full_name": "LiveCodeBench/LiveCodeBench", "kind": "benchmark_source", "resolution_status": "resolved", "subpath": null, "url": "https://github.com/LiveCodeBench/LiveCodeBench"}, "resolution_status": "resolved", "source": "reviewed_llm_stats_identity_override", "source_path": "data/catalog/llm_stats_identity_overrides.yml"}, "key": "llm-stats:livecodebench-v6", "modality": "text", "name": "LiveCodeBench v6", "openness": {"access_gate": null, "basis": "reviewed_data_availability_not_established", "code_license": null, "code_license_note": null, "data_license": null, "data_license_note": null, "data_located": null, "evidence": ["https://github.com/LiveCodeBench/LiveCodeBench"], "link_status": null, "status": "unknown"}, "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/livecodebench-v6?top_n=500"}, "publisher": null, "released": null, "released_reference": null, "repository": {"full_name": "LiveCodeBench/LiveCodeBench", "kind": "benchmark_source", "resolution_status": "resolved", "subpath": null, "url": "https://github.com/LiveCodeBench/LiveCodeBench"}, "schema_version": 1, "sizes": [], "slug": "llm-stats-livecodebench-v6", "source": "llm_stats", "source_benchmark_id": "livecodebench-v6"}, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.7-max", "model_name": "Qwen3.7 Max", "obs_id": "llm_stats:livecodebench-v6:qwen3.7-max", "organization": "Qwen", "rank_in_source_response": 1, "raw_value": "0.916", "reported_by": "self_reported", "reported_date": "2026-05-19", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.916, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "sakana-namazu", "model_name": "Sakana Namazu", "obs_id": "llm_stats:livecodebench-v6:sakana-namazu", "organization": "Sakana AI", "rank_in_source_response": 2, "raw_value": "0.9033", "reported_by": "self_reported", "reported_date": "2026-08-03", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.9033, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.8-27b", "model_name": "Qwen3.8-27B", "obs_id": "llm_stats:livecodebench-v6:qwen3.8-27b", "organization": "Qwen", "rank_in_source_response": 3, "raw_value": "0.903", "reported_by": "self_reported", "reported_date": "2026-08-14", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.903, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.7-plus", "model_name": "Qwen3.7-Plus", "obs_id": "llm_stats:livecodebench-v6:qwen3.7-plus", "organization": "Qwen", "rank_in_source_response": 4, "raw_value": "0.896", "reported_by": "self_reported", "reported_date": "2026-05-31", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.896, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "kimi-k2.6", "model_name": "Kimi K2.6", "obs_id": "llm_stats:livecodebench-v6:kimi-k2.6", "organization": "Moonshot AI", "rank_in_source_response": 5, "raw_value": "0.896", "reported_by": "self_reported", "reported_date": "2026-04-20", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.896, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra (550B A55B)", "obs_id": "llm_stats:livecodebench-v6:nemotron-3-ultra-550b-a55b", "organization": "NVIDIA", "rank_in_source_response": 6, "raw_value": "0.89", "reported_by": "self_reported", "reported_date": "2026-06-04", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.89, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "seed-2.0-pro", "model_name": "Seed 2.0 Pro", "obs_id": "llm_stats:livecodebench-v6:seed-2.0-pro", "organization": "ByteDance", "rank_in_source_response": 7, "raw_value": "0.878", "reported_by": "self_reported", "reported_date": "2026-02-14", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.878, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "mai-thinking-1", "model_name": "MAI-Thinking-1", "obs_id": "llm_stats:livecodebench-v6:mai-thinking-1", "organization": "Microsoft", "rank_in_source_response": 8, "raw_value": "0.877", "reported_by": "self_reported", "reported_date": "2026-06-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.877, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.6-plus", "model_name": "Qwen3.6 Plus", "obs_id": "llm_stats:livecodebench-v6:qwen3.6-plus", "organization": "Qwen", "rank_in_source_response": 9, "raw_value": "0.871", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.871, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "step-3.5-flash", "model_name": "Step-3.5-Flash", "obs_id": "llm_stats:livecodebench-v6:step-3.5-flash", "organization": "StepFun", "rank_in_source_response": 10, "raw_value": "0.864", "reported_by": "self_reported", "reported_date": "2026-02-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.864, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "kimi-k2.5", "model_name": "Kimi K2.5", "obs_id": "llm_stats:livecodebench-v6:kimi-k2.5", "organization": "Moonshot AI", "rank_in_source_response": 11, "raw_value": "0.85", "reported_by": "self_reported", "reported_date": "2026-01-27", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.85, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "glm-4.7", "model_name": "GLM-4.7", "obs_id": "llm_stats:livecodebench-v6:glm-4.7", "organization": "Z.ai", "rank_in_source_response": 12, "raw_value": "0.849", "reported_by": "self_reported", "reported_date": "2025-12-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.849, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.6-27b", "model_name": "Qwen3.6-27B", "obs_id": "llm_stats:livecodebench-v6:qwen3.6-27b", "organization": "Qwen", "rank_in_source_response": 13, "raw_value": "0.839", "reported_by": "self_reported", "reported_date": "2026-04-21", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.839, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.5-397b-a17b", "model_name": "Qwen3.5-397B-A17B", "obs_id": "llm_stats:livecodebench-v6:qwen3.5-397b-a17b", "organization": "Qwen", "rank_in_source_response": 14, "raw_value": "0.836", "reported_by": "self_reported", "reported_date": "2026-02-16", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.836, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "kimi-k2-thinking-0905", "model_name": "Kimi K2-Thinking-0905", "obs_id": "llm_stats:livecodebench-v6:kimi-k2-thinking-0905", "organization": "Moonshot AI", "rank_in_source_response": 15, "raw_value": "0.831", "reported_by": "self_reported", "reported_date": "2025-09-05", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.831, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "glm-4.6", "model_name": "GLM-4.6", "obs_id": "llm_stats:livecodebench-v6:glm-4.6", "organization": "Z.ai", "rank_in_source_response": 16, "raw_value": "0.828", "reported_by": "self_reported", "reported_date": "2025-09-30", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.828, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "gpt-oss-120b-high", "model_name": "GPT OSS 120B High", "obs_id": "llm_stats:livecodebench-v6:gpt-oss-120b-high", "organization": "OpenAI", "rank_in_source_response": 17, "raw_value": "0.819", "reported_by": "self_reported", "reported_date": "2025-08-05", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.819, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "seed-2.0-lite", "model_name": "Seed 2.0 Lite", "obs_id": "llm_stats:livecodebench-v6:seed-2.0-lite", "organization": "ByteDance", "rank_in_source_response": 18, "raw_value": "0.817", "reported_by": "self_reported", "reported_date": "2026-02-14", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.817, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.5-27b", "model_name": "Qwen3.5-27B", "obs_id": "llm_stats:livecodebench-v6:qwen3.5-27b", "organization": "Qwen", "rank_in_source_response": 19, "raw_value": "0.807", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.807, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "k-exaone-236b-a23b", "model_name": "K-EXAONE-236B-A23B", "obs_id": "llm_stats:livecodebench-v6:k-exaone-236b-a23b", "organization": "LG AI Research", "rank_in_source_response": 20, "raw_value": "0.807", "reported_by": "self_reported", "reported_date": "2025-12-31", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.807, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "mimo-v2-flash", "model_name": "MiMo-V2-Flash", "obs_id": "llm_stats:livecodebench-v6:mimo-v2-flash", "organization": "Xiaomi", "rank_in_source_response": 21, "raw_value": "0.806", "reported_by": "self_reported", "reported_date": "2025-12-16", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.806, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.6-35b-a3b", "model_name": "Qwen3.6-35B-A3B", "obs_id": "llm_stats:livecodebench-v6:qwen3.6-35b-a3b", "organization": "Qwen", "rank_in_source_response": 22, "raw_value": "0.804", "reported_by": "self_reported", "reported_date": "2026-04-16", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "gemma-4-31b-it", "model_name": "Gemma 4 31B", "obs_id": "llm_stats:livecodebench-v6:gemma-4-31b-it", "organization": "Google", "rank_in_source_response": 23, "raw_value": "0.8", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.8, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.5-122b-a10b", "model_name": "Qwen3.5-122B-A10B", "obs_id": "llm_stats:livecodebench-v6:qwen3.5-122b-a10b", "organization": "Qwen", "rank_in_source_response": 24, "raw_value": "0.789", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.789, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "gemma-4-26b-a4b-it", "model_name": "Gemma 4 26B-A4B", "obs_id": "llm_stats:livecodebench-v6:gemma-4-26b-a4b-it", "organization": "Google", "rank_in_source_response": 25, "raw_value": "0.771", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.771, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.5-35b-a3b", "model_name": "Qwen3.5-35B-A3B", "obs_id": "llm_stats:livecodebench-v6:qwen3.5-35b-a3b", "organization": "Qwen", "rank_in_source_response": 26, "raw_value": "0.746", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-235b-a22b-thinking-2507", "model_name": "Qwen3-235B-A22B-Thinking-2507", "obs_id": "llm_stats:livecodebench-v6:qwen3-235b-a22b-thinking-2507", "organization": "Qwen", "rank_in_source_response": 27, "raw_value": "0.741", "reported_by": "self_reported", "reported_date": "2025-07-25", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.741, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "gemma-4-12b-it", "model_name": "Gemma 4 12B", "obs_id": "llm_stats:livecodebench-v6:gemma-4-12b-it", "organization": "Google", "rank_in_source_response": 28, "raw_value": "0.72", "reported_by": "self_reported", "reported_date": "2026-05-23", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.72, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "sarvam-105b", "model_name": "Sarvam-105B", "obs_id": "llm_stats:livecodebench-v6:sarvam-105b", "organization": "Sarvam AI", "rank_in_source_response": 29, "raw_value": "0.717", "reported_by": "self_reported", "reported_date": "2026-03-06", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.717, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "north-mini-code-1.0", "model_name": "North Mini Code 1.0", "obs_id": "llm_stats:livecodebench-v6:north-mini-code-1.0", "organization": "Cohere", "rank_in_source_response": 30, "raw_value": "0.703", "reported_by": "self_reported", "reported_date": "2026-06-09", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 VL 235B A22B Thinking", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-235b-a22b-thinking", "organization": "Qwen", "rank_in_source_response": 31, "raw_value": "0.701", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.701, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "sarvam-30b", "model_name": "Sarvam-30B", "obs_id": "llm_stats:livecodebench-v6:sarvam-30b", "organization": "Sarvam AI", "rank_in_source_response": 32, "raw_value": "0.7", "reported_by": "self_reported", "reported_date": "2026-03-06", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.7, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "diffusiongemma-26b-a4b-it", "model_name": "DiffusionGemma 26B-A4B", "obs_id": "llm_stats:livecodebench-v6:diffusiongemma-26b-a4b-it", "organization": "Google", "rank_in_source_response": 33, "raw_value": "0.691", "reported_by": "self_reported", "reported_date": "2026-06-10", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.691, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-max", "model_name": "Qwen3 Max", "obs_id": "llm_stats:livecodebench-v6:qwen3-max", "organization": "Qwen", "rank_in_source_response": 34, "raw_value": "0.69", "reported_by": "self_reported", "reported_date": "2025-12-15", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-next-80b-a3b-thinking", "model_name": "Qwen3-Next-80B-A3B-Thinking", "obs_id": "llm_stats:livecodebench-v6:qwen3-next-80b-a3b-thinking", "organization": "Qwen", "rank_in_source_response": 35, "raw_value": "0.687", "reported_by": "self_reported", "reported_date": "2025-09-10", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.687, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "nemotron-3-nano-30b-a3b", "model_name": "Nemotron 3 Nano (30B A3B)", "obs_id": "llm_stats:livecodebench-v6:nemotron-3-nano-30b-a3b", "organization": "NVIDIA", "rank_in_source_response": 36, "raw_value": "0.683", "reported_by": "self_reported", "reported_date": "2025-12-15", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.683, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.5-9b", "model_name": "Qwen3.5-9B", "obs_id": "llm_stats:livecodebench-v6:qwen3.5-9b", "organization": "Qwen", "rank_in_source_response": 37, "raw_value": "0.656", "reported_by": "self_reported", "reported_date": "2026-03-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.656, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-32b-thinking", "model_name": "Qwen3 VL 32B Thinking", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-32b-thinking", "organization": "Qwen", "rank_in_source_response": 38, "raw_value": "0.656", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.656, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-30b-a3b-thinking", "model_name": "Qwen3 VL 30B A3B Thinking", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-30b-a3b-thinking", "organization": "Qwen", "rank_in_source_response": 39, "raw_value": "0.642", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.642, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "lfm-2.5-2.6b", "model_name": "LFM2.5-2.6B", "obs_id": "llm_stats:livecodebench-v6:lfm-2.5-2.6b", "organization": "Liquid AI", "rank_in_source_response": 40, "raw_value": "0.5941", "reported_by": "self_reported", "reported_date": "2026-08-04", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.5941, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-8b-thinking", "model_name": "Qwen3 VL 8B Thinking", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-8b-thinking", "organization": "Qwen", "rank_in_source_response": 41, "raw_value": "0.586", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.586, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-next-80b-a3b-instruct", "model_name": "Qwen3-Next-80B-A3B-Instruct", "obs_id": "llm_stats:livecodebench-v6:qwen3-next-80b-a3b-instruct", "organization": "Qwen", "rank_in_source_response": 42, "raw_value": "0.566", "reported_by": "self_reported", "reported_date": "2025-09-10", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3.5-4b", "model_name": "Qwen3.5-4B", "obs_id": "llm_stats:livecodebench-v6:qwen3.5-4b", "organization": "Qwen", "rank_in_source_response": 43, "raw_value": "0.558", "reported_by": "self_reported", "reported_date": "2026-03-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.558, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-235b-a22b-instruct", "model_name": "Qwen3 VL 235B A22B Instruct", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-235b-a22b-instruct", "organization": "Qwen", "rank_in_source_response": 44, "raw_value": "0.543", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.543, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "kimi-k2-instruct", "model_name": "Kimi K2 Instruct", "obs_id": "llm_stats:livecodebench-v6:kimi-k2-instruct", "organization": "Moonshot AI", "rank_in_source_response": 45, "raw_value": "0.537", "reported_by": "self_reported", "reported_date": "2025-07-11", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.537, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "gemma-4-e4b-it", "model_name": "Gemma 4 E4B", "obs_id": "llm_stats:livecodebench-v6:gemma-4-e4b-it", "organization": "Google", "rank_in_source_response": 46, "raw_value": "0.52", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.52, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "minicpm-sala", "model_name": "MiniCPM-SALA", "obs_id": "llm_stats:livecodebench-v6:minicpm-sala", "organization": "OpenBMB", "rank_in_source_response": 47, "raw_value": "0.52", "reported_by": "self_reported", "reported_date": "2026-02-11", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.52, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-235b-a22b-instruct-2507", "model_name": "Qwen3-235B-A22B-Instruct-2507", "obs_id": "llm_stats:livecodebench-v6:qwen3-235b-a22b-instruct-2507", "organization": "Qwen", "rank_in_source_response": 48, "raw_value": "0.518", "reported_by": "self_reported", "reported_date": "2025-07-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.518, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-4b-thinking", "model_name": "Qwen3 VL 4B Thinking", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-4b-thinking", "organization": "Qwen", "rank_in_source_response": 49, "raw_value": "0.513", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.513, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "gemma-4-e2b-it", "model_name": "Gemma 4 E2B", "obs_id": "llm_stats:livecodebench-v6:gemma-4-e2b-it", "organization": "Google", "rank_in_source_response": 50, "raw_value": "0.44", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.44, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-32b-instruct", "model_name": "Qwen3 VL 32B Instruct", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-32b-instruct", "organization": "Qwen", "rank_in_source_response": 51, "raw_value": "0.438", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.438, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-30b-a3b-instruct", "model_name": "Qwen3 VL 30B A3B Instruct", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-30b-a3b-instruct", "organization": "Qwen", "rank_in_source_response": 52, "raw_value": "0.426", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.426, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "mimo-v2.5-pro", "model_name": "MiMo-V2.5-Pro", "obs_id": "llm_stats:livecodebench-v6:mimo-v2.5-pro", "organization": "Xiaomi", "rank_in_source_response": 53, "raw_value": "0.396", "reported_by": "self_reported", "reported_date": "2026-04-27", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.396, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-8b-instruct", "model_name": "Qwen3 VL 8B Instruct", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-8b-instruct", "organization": "Qwen", "rank_in_source_response": 54, "raw_value": "0.393", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.393, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "qwen3-vl-4b-instruct", "model_name": "Qwen3 VL 4B Instruct", "obs_id": "llm_stats:livecodebench-v6:qwen3-vl-4b-instruct", "organization": "Qwen", "rank_in_source_response": 55, "raw_value": "0.379", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.379, "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/livecodebench-v6?top_n=500", "key": "llm-stats:livecodebench-v6", "measured_by": null, "model_id": "kimi-k2-base", "model_name": "Kimi K2 Base", "obs_id": "llm_stats:livecodebench-v6:kimi-k2-base", "organization": "Moonshot AI", "rank_in_source_response": 56, "raw_value": "0.263", "reported_by": "self_reported", "reported_date": "2025-07-11", "series_id": "llm_stats:livecodebench-v6:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500", "value": 0.263, "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:livecodebench-v6:kimi-k2-base", "reported_at": "2025-07-11", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500"}, "first_score_report": null, "key": "llm-stats:livecodebench-v6", "max_score_contradicted": false, "metric": null, "observation_count": 56, "observed_max": 0.916, "score_summary": {"display_max": 91.60000000000001, "display_multiplier": 100, "model_count": 56, "model_count_basis": "source_model_id", "numeric_count": 56, "raw_max": 0.916, "raw_min": 0.263, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:livecodebench-v6:qwen3.7-max", "reported_date": "2026-05-19", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/livecodebench-v6?top_n=500"}, "unit": null}, "series_id": "llm_stats:livecodebench-v6:default"}}}, "siblings": [{"key": "opencompass:1413", "name": "LiveCodeBench", "relation": "variant:of", "slug": "opencompass-1413-livecodebench", "source": "opencompass_hub"}]}
