{"record": {"aliases": [], "artifacts": [], "categories": ["math", "reasoning"], "description": {"en": "CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500", "title": "CritPT"}], "evidence_summary": {"document_count": 1, "model_count": 5, "model_count_basis": "source_model_id"}, "key": "llm-stats:critpt", "modality": "text", "name": "CritPT", "openness": {"code_license": null, "data_license": null, "evidence": [], "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/critpt?top_n=500"}, "publisher": null, "released": null, "released_reference": null, "schema_version": 1, "sizes": [], "slug": "llm-stats-critpt", "source": "llm_stats", "source_benchmark_id": "critpt"}, "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/critpt?top_n=500", "key": "llm-stats:critpt", "measured_by": null, "model_id": "glm-5.2", "model_name": "GLM-5.2", "obs_id": "llm_stats:critpt:glm-5.2", "organization": "Z.ai", "rank_in_source_response": 1, "raw_value": "0.167", "reported_by": "self_reported", "reported_date": "2026-06-16", "series_id": "llm_stats:critpt:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?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/critpt?top_n=500", "key": "llm-stats:critpt", "measured_by": null, "model_id": "qwen3.7-max", "model_name": "Qwen3.7 Max", "obs_id": "llm_stats:critpt:qwen3.7-max", "organization": "Qwen", "rank_in_source_response": 2, "raw_value": "0.114", "reported_by": "self_reported", "reported_date": "2026-05-19", "series_id": "llm_stats:critpt:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500", "value": 0.114, "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/critpt?top_n=500", "key": "llm-stats:critpt", "measured_by": null, "model_id": "inkling-small", "model_name": "Inkling-Small", "obs_id": "llm_stats:critpt:inkling-small", "organization": "Thinking Machines Lab", "rank_in_source_response": 3, "raw_value": "0.083", "reported_by": "self_reported", "reported_date": "2026-07-30", "series_id": "llm_stats:critpt:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500", "value": 0.083, "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/critpt?top_n=500", "key": "llm-stats:critpt", "measured_by": null, "model_id": "qwen3.7-plus", "model_name": "Qwen3.7-Plus", "obs_id": "llm_stats:critpt:qwen3.7-plus", "organization": "Qwen", "rank_in_source_response": 4, "raw_value": "0.06", "reported_by": "self_reported", "reported_date": "2026-05-31", "series_id": "llm_stats:critpt:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500", "value": 0.06, "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/critpt?top_n=500", "key": "llm-stats:critpt", "measured_by": null, "model_id": "nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra (550B A55B)", "obs_id": "llm_stats:critpt:nemotron-3-ultra-550b-a55b", "organization": "NVIDIA", "rank_in_source_response": 5, "raw_value": "0.031", "reported_by": "self_reported", "reported_date": "2026-06-04", "series_id": "llm_stats:critpt:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500", "value": 0.031, "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:critpt:qwen3.7-max", "reported_at": "2026-05-19", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500"}, "first_score_report": null, "key": "llm-stats:critpt", "max_score_contradicted": false, "metric": null, "observation_count": 5, "observed_max": 0.167, "score_summary": {"display_max": 16.7, "display_multiplier": 100, "model_count": 5, "model_count_basis": "source_model_id", "numeric_count": 5, "raw_max": 0.167, "raw_min": 0.031, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:critpt:glm-5.2", "reported_date": "2026-06-16", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/critpt?top_n=500"}, "unit": null}, "series_id": "llm_stats:critpt:default"}}}, "siblings": []}
