{"adoption": {"forks": 182, "observed_at": "2026-08-28T04:04:51.344476+00:00", "stars": 1484}, "canonical_url": "https://ross.abutalabs.com/products/llm-colosseum", "card": {"archived": false, "artifact_type": "application", "description": "Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM", "domain": ["large-language-models", "artificial-intelligence", "gaming-tools", "analytics"], "enriched": true, "function": ["benchmarking", "llm-inference", "agent-framework", "machine-learning"], "health_score": 37, "homepage": "https://llm-colosseum.phospho.ai", "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["OpenGenerativeAI/llm-colosseum"], "name": "OpenGenerativeAI/llm-colosseum", "platform": ["python", "browser"], "pushed_at": "2025-03-21T10:35:26+00:00", "repo": "OpenGenerativeAI/llm-colosseum", "stars": 1484, "tags": ["llm-evaluation", "elo-ranking", "street-fighter", "game-benchmark", "reinforcement-learning-comparison", "jupyter-notebook", "web", "desktop"], "topics": ["genai", "llm", "benchmark", "streetfighterai"], "urls": [], "use_cases": ["benchmark llms by playing street fighter", "compare llm decision making in real time", "elo ranking of large language models", "evaluate llm agents in a game environment", "test which ai model is the best fighter", "alternative llm benchmark beyond static tests"], "what_it_is": "LLM Colosseum is a benchmarking tool that pits large language models against each other in real-time Street Fighter III matches to evaluate their decision-making quality. It produces an ELO-based leaderboard from hundreds of automated fights between models like GPT-4o, Pixtral, Claude, and Llama.", "when_to_avoid": ["you need rigorous, reproducible academic benchmarks", "you need standard NLP task evaluation like MMLU or code generation", "you need a production LLM evaluation pipeline"], "when_to_choose": ["you want a novel, real-time evaluation of LLM reasoning and adaptability", "you want to compare vision and text modes of frontier models in an interactive setting", "you want an entertaining demo of LLM agent capabilities"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-colosseum", "repo": "OpenGenerativeAI/llm-colosseum", "role": "main", "score": 28}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.344476+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:33:58.324344+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f830e0bc546d25504996a2cb5aac3688b7c3b7e9b6a6da94ce0f8708d9f3da86", "fetched_at": "2026-08-28T04:04:51.344476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGenerativeAI/llm-colosseum"}, {"content_hash": "a6873599d06fd7e23cc3684cfd9e441981a62386737b411cb361d9e1372a1ed2", "fetched_at": "2026-08-29T11:40:17.184252+00:00", "kind": "homepage", "missing": false, "url": "https://llm-colosseum.phospho.ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 12, "longevity": 63, "rhythm": 28}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 893, "days_push": 530, "days_rel": 651, "gap_med": 41, "n_releases_24m": 2}, "score": 28, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}