{"record": {"aliases": [], "artifacts": [{"id": "arxiv:1803.05457", "kind": "paper", "locator": "linked URL", "url": "https://arxiv.org/pdf/1803.05457.pdf"}], "categories": ["reasoning", "general"], "description": {"en": "The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities. ARC-C specifically contains questions that were answered incorrectly by both retrieval-based and word co-occurrence algorithms, making it a particularly challenging subset designed to test commonsense reasoning abilities in AI systems."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "title": "ARC-C"}], "evidence_summary": {"document_count": 1, "model_count": 34, "model_count_basis": "source_model_id"}, "identity_inheritance": {"donor_key": "opencompass:502", "donor_name": "ARC-c", "donor_source": "opencompass_hub", "fields": ["artifacts", "released"], "group_id": "arc-c", "reviewed_at": "2026-08-22", "reviewed_by": "ktwu01"}, "identity_override": {"candidate_matches": [{"note": "Official dataset distribution page, not a GitHub repository.", "url": "https://allenai.org/data/arc"}, {"note": "Baseline solvers rather than the benchmark source.", "url": "https://github.com/allenai/ARC-Solvers"}], "evidence": [], "note": "ARC-Challenge has official data distribution but no verified source repository.", "repository": {"full_name": null, "kind": "not_found", "resolution_status": "not_found", "subpath": null, "url": null}, "resolution_status": "not_found", "source": "reviewed_llm_stats_identity_override", "source_path": "data/catalog/llm_stats_identity_overrides.yml"}, "key": "llm-stats:arc-c", "modality": "text", "name": "ARC-C", "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": [], "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/arc-c?top_n=500"}, "publisher": null, "released": "2018-03-14", "released_reference": {"basis": "paper_first_version", "note": "The ARC introduction releases both the Challenge and Easy partitions.", "source_key": "opencompass:502", "source_url": "https://arxiv.org/abs/1803.05457"}, "repository": {"full_name": null, "kind": "not_found", "resolution_status": "not_found", "subpath": null, "url": null}, "schema_version": 1, "sizes": [], "slug": "llm-stats-arc-c", "source": "llm_stats", "source_benchmark_id": "arc-c"}, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "mimo-v2.5-pro", "model_name": "MiMo-V2.5-Pro", "obs_id": "llm_stats:arc-c:mimo-v2.5-pro", "organization": "Xiaomi", "rank_in_source_response": 1, "raw_value": "0.972", "reported_by": "self_reported", "reported_date": "2026-04-27", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.972, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "llama-3.1-405b-instruct", "model_name": "Llama 3.1 405B Instruct", "obs_id": "llm_stats:arc-c:llama-3.1-405b-instruct", "organization": "Meta", "rank_in_source_response": 2, "raw_value": "0.969", "reported_by": "self_reported", "reported_date": "2024-07-23", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.969, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "claude-3-opus-20240229", "model_name": "Claude 3 Opus", "obs_id": "llm_stats:arc-c:claude-3-opus-20240229", "organization": "Anthropic", "rank_in_source_response": 3, "raw_value": "0.964", "reported_by": "self_reported", "reported_date": "2024-02-29", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.964, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "nova-pro", "model_name": "Nova Pro", "obs_id": "llm_stats:arc-c:nova-pro", "organization": "Amazon", "rank_in_source_response": 4, "raw_value": "0.948", "reported_by": "self_reported", "reported_date": "2024-11-20", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.948, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "llama-3.1-70b-instruct", "model_name": "Llama 3.1 70B Instruct", "obs_id": "llm_stats:arc-c:llama-3.1-70b-instruct", "organization": "Meta", "rank_in_source_response": 5, "raw_value": "0.948", "reported_by": "self_reported", "reported_date": "2024-07-23", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.948, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "claude-3-sonnet-20240229", "model_name": "Claude 3 Sonnet", "obs_id": "llm_stats:arc-c:claude-3-sonnet-20240229", "organization": "Anthropic", "rank_in_source_response": 6, "raw_value": "0.932", "reported_by": "self_reported", "reported_date": "2024-02-29", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.932, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "jamba-1.5-large", "model_name": "Jamba 1.5 Large", "obs_id": "llm_stats:arc-c:jamba-1.5-large", "organization": "AI21 Labs", "rank_in_source_response": 7, "raw_value": "0.93", "reported_by": "self_reported", "reported_date": "2024-08-22", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.93, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "nova-lite", "model_name": "Nova Lite", "obs_id": "llm_stats:arc-c:nova-lite", "organization": "Amazon", "rank_in_source_response": 8, "raw_value": "0.924", "reported_by": "self_reported", "reported_date": "2024-11-20", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.924, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "mistral-small-24b-base-2501", "model_name": "Mistral Small 3 24B Base", "obs_id": "llm_stats:arc-c:mistral-small-24b-base-2501", "organization": "Mistral", "rank_in_source_response": 9, "raw_value": "0.9129", "reported_by": "self_reported", "reported_date": "2025-01-30", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.9129, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "phi-3.5-moe-instruct", "model_name": "Phi-3.5-MoE-instruct", "obs_id": "llm_stats:arc-c:phi-3.5-moe-instruct", "organization": "Microsoft", "rank_in_source_response": 10, "raw_value": "0.91", "reported_by": "self_reported", "reported_date": "2024-08-23", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.91, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "nova-micro", "model_name": "Nova Micro", "obs_id": "llm_stats:arc-c:nova-micro", "organization": "Amazon", "rank_in_source_response": 11, "raw_value": "0.902", "reported_by": "self_reported", "reported_date": "2024-11-20", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.902, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "claude-3-haiku-20240307", "model_name": "Claude 3 Haiku", "obs_id": "llm_stats:arc-c:claude-3-haiku-20240307", "organization": "Anthropic", "rank_in_source_response": 12, "raw_value": "0.892", "reported_by": "self_reported", "reported_date": "2024-03-13", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.892, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "jamba-1.5-mini", "model_name": "Jamba 1.5 Mini", "obs_id": "llm_stats:arc-c:jamba-1.5-mini", "organization": "AI21 Labs", "rank_in_source_response": 13, "raw_value": "0.857", "reported_by": "self_reported", "reported_date": "2024-08-22", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.857, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "phi-3.5-mini-instruct", "model_name": "Phi-3.5-mini-instruct", "obs_id": "llm_stats:arc-c:phi-3.5-mini-instruct", "organization": "Microsoft", "rank_in_source_response": 14, "raw_value": "0.846", "reported_by": "self_reported", "reported_date": "2024-08-23", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.846, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "phi-4-mini", "model_name": "Phi 4 Mini", "obs_id": "llm_stats:arc-c:phi-4-mini", "organization": "Microsoft", "rank_in_source_response": 15, "raw_value": "0.837", "reported_by": "self_reported", "reported_date": "2025-02-01", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.837, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "llama-3.1-8b-instruct", "model_name": "Llama 3.1 8B Instruct", "obs_id": "llm_stats:arc-c:llama-3.1-8b-instruct", "organization": "Meta", "rank_in_source_response": 16, "raw_value": "0.834", "reported_by": "self_reported", "reported_date": "2024-07-23", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.834, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "llama-3.2-3b-instruct", "model_name": "Llama 3.2 3B Instruct", "obs_id": "llm_stats:arc-c:llama-3.2-3b-instruct", "organization": "Meta", "rank_in_source_response": 17, "raw_value": "0.786", "reported_by": "self_reported", "reported_date": "2024-09-25", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.786, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "ministral-8b-instruct-2410", "model_name": "Ministral 8B Instruct", "obs_id": "llm_stats:arc-c:ministral-8b-instruct-2410", "organization": "Mistral", "rank_in_source_response": 18, "raw_value": "0.719", "reported_by": "self_reported", "reported_date": "2024-10-16", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.719, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "gemma-2-27b-it", "model_name": "Gemma 2 27B", "obs_id": "llm_stats:arc-c:gemma-2-27b-it", "organization": "Google", "rank_in_source_response": 19, "raw_value": "0.714", "reported_by": "self_reported", "reported_date": "2024-06-27", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.714, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "command-r-plus-04-2024", "model_name": "Command R+", "obs_id": "llm_stats:arc-c:command-r-plus-04-2024", "organization": "Cohere", "rank_in_source_response": 20, "raw_value": "0.7099", "reported_by": "self_reported", "reported_date": "2024-08-30", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.7099, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "qwen-2.5-coder-32b-instruct", "model_name": "Qwen2.5-Coder 32B Instruct", "obs_id": "llm_stats:arc-c:qwen-2.5-coder-32b-instruct", "organization": "Qwen", "rank_in_source_response": 21, "raw_value": "0.705", "reported_by": "self_reported", "reported_date": "2024-09-19", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.705, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "qwen-2.5-32b-instruct", "model_name": "Qwen2.5 32B Instruct", "obs_id": "llm_stats:arc-c:qwen-2.5-32b-instruct", "organization": "Qwen", "rank_in_source_response": 22, "raw_value": "0.704", "reported_by": "self_reported", "reported_date": "2024-09-19", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.704, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "llama-3.1-nemotron-70b-instruct", "model_name": "Llama 3.1 Nemotron 70B Instruct", "obs_id": "llm_stats:arc-c:llama-3.1-nemotron-70b-instruct", "organization": "NVIDIA", "rank_in_source_response": 23, "raw_value": "0.692", "reported_by": "self_reported", "reported_date": "2024-10-01", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.692, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "qwen2-72b-instruct", "model_name": "Qwen2 72B Instruct", "obs_id": "llm_stats:arc-c:qwen2-72b-instruct", "organization": "Qwen", "rank_in_source_response": 24, "raw_value": "0.689", "reported_by": "self_reported", "reported_date": "2024-07-23", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.689, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "gemma-2-9b-it", "model_name": "Gemma 2 9B", "obs_id": "llm_stats:arc-c:gemma-2-9b-it", "organization": "Google", "rank_in_source_response": 25, "raw_value": "0.684", "reported_by": "self_reported", "reported_date": "2024-06-27", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "qwen-2.5-14b-instruct", "model_name": "Qwen2.5 14B Instruct", "obs_id": "llm_stats:arc-c:qwen-2.5-14b-instruct", "organization": "Qwen", "rank_in_source_response": 26, "raw_value": "0.673", "reported_by": "self_reported", "reported_date": "2024-09-19", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.673, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "hermes-3-70b", "model_name": "Hermes 3 70B", "obs_id": "llm_stats:arc-c:hermes-3-70b", "organization": "Nous Research", "rank_in_source_response": 27, "raw_value": "0.6553", "reported_by": "self_reported", "reported_date": "2024-08-15", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.6553, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "gemma-3n-e4b", "model_name": "Gemma 3n E4B", "obs_id": "llm_stats:arc-c:gemma-3n-e4b", "organization": "Google", "rank_in_source_response": 28, "raw_value": "0.616", "reported_by": "self_reported", "reported_date": "2025-06-26", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "gemma-3n-e4b-it-litert-preview", "model_name": "Gemma 3n E4B Instructed LiteRT Preview", "obs_id": "llm_stats:arc-c:gemma-3n-e4b-it-litert-preview", "organization": "Google", "rank_in_source_response": 29, "raw_value": "0.616", "reported_by": "self_reported", "reported_date": "2025-05-20", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "qwen-2.5-coder-7b-instruct", "model_name": "Qwen2.5-Coder 7B Instruct", "obs_id": "llm_stats:arc-c:qwen-2.5-coder-7b-instruct", "organization": "Qwen", "rank_in_source_response": 30, "raw_value": "0.609", "reported_by": "self_reported", "reported_date": "2024-09-19", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.609, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "gemma-3n-e2b", "model_name": "Gemma 3n E2B", "obs_id": "llm_stats:arc-c:gemma-3n-e2b", "organization": "Google", "rank_in_source_response": 31, "raw_value": "0.517", "reported_by": "self_reported", "reported_date": "2025-06-26", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.517, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "gemma-3n-e2b-it-litert-preview", "model_name": "Gemma 3n E2B Instructed LiteRT (Preview)", "obs_id": "llm_stats:arc-c:gemma-3n-e2b-it-litert-preview", "organization": "Google", "rank_in_source_response": 32, "raw_value": "0.517", "reported_by": "self_reported", "reported_date": "2025-05-20", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.517, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "granite-3.3-8b-base", "model_name": "Granite 3.3 8B Base", "obs_id": "llm_stats:arc-c:granite-3.3-8b-base", "organization": "IBM", "rank_in_source_response": 33, "raw_value": "0.5084", "reported_by": "self_reported", "reported_date": "2025-04-16", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.5084, "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/arc-c?top_n=500", "key": "llm-stats:arc-c", "measured_by": null, "model_id": "ernie-4.5", "model_name": "ERNIE 4.5", "obs_id": "llm_stats:arc-c:ernie-4.5", "organization": "Baidu", "rank_in_source_response": 34, "raw_value": "0.406", "reported_by": "self_reported", "reported_date": "2025-06-25", "series_id": "llm_stats:arc-c:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500", "value": 0.406, "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:arc-c:claude-3-opus-20240229", "reported_at": "2024-02-29", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500"}, "first_score_report": null, "key": "llm-stats:arc-c", "max_score_contradicted": false, "metric": null, "observation_count": 34, "observed_max": 0.972, "score_summary": {"display_max": 97.2, "display_multiplier": 100, "model_count": 34, "model_count_basis": "source_model_id", "numeric_count": 34, "raw_max": 0.972, "raw_min": 0.406, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:arc-c:mimo-v2.5-pro", "reported_date": "2026-04-27", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/arc-c?top_n=500"}, "unit": null}, "series_id": "llm_stats:arc-c:default"}}}, "siblings": [{"key": "opencompass:502", "name": "ARC-c", "relation": "equivalent", "slug": "opencompass-502-arc-c", "source": "opencompass_hub"}]}
