[{"family":"anthropic","records":60,"currentBests":6,"uncontestedBests":1,"competitions":[{"id":"mle-bench","name":"MLE-bench","records":4,"bests":0},{"id":"lora-speedrun","name":"LoRA Speedrun","records":1,"bests":0},{"id":"sokoban-speedrun","name":"Sokoban Speedrun","records":1,"bests":1},{"id":"lean-eval","name":"LeanEval","records":16,"bests":0},{"id":"gpu-mode-reference-kernels","name":"GPU Mode Reference Kernels","records":1,"bests":0},{"id":"chi-bench","name":"CHI-Bench","records":32,"bests":4},{"id":"programbench","name":"ProgramBench","records":3,"bests":0},{"id":"sutro-problems","name":"Sutro Problems","records":2,"bests":1}],"models":{"Claude-Opus-4.6":4,"Claude Fable 5":2,"Claude Opus 4.8 (1M context)":1,"Claude Opus 5":1,"GPT-5.5 (human-in-the-loop)":1,"OSS contributions":1,"Fable 5 (multi-agent)":2,"Opus 4.8) + GPT-5.6-Sol":2,"Antigravity (Multi-Model Ensemble: Gemini 3.1 Pro, Gemini 3 Flash, Claude 4.6 Sonnet/Opus)":1,"Claude Opus 4.7 (1M context)":2,"GPT-5.6 and Fable 5 (human-in-the-loop)":1,"Fable 5 and GPT-5.6":1,"Claude Fable 5 (Claude Code)":1,"Claude Fable 5 (orchestrating Opus/Sonnet 4.8)":1,"OpenAI Codex (GPT-5.6 Sol), Claude Code (Opus 5 and Opus 4.8)":1,"Claude Opus 4.6 (1M context)":1,"anthropic/claude-opus-5":8,"anthropic/claude-opus-4-8":12,"anthropic/claude-opus-4-6":4,"anthropic/claude-fable-5":4,"anthropic/claude-sonnet-5":4,"Claude Opus 4.6":1,"Claude Sonnet 4.6":2,"Claude Haiku 4.5":1,"Claude Fable 5.1":1},"tools":{"Claude Code":2,"Humanize2 flame chase: GPT-5.6-sol":1,"Claude Opus 4.7":1,"Claude Opus 4.7, 4.8 and Fable 5":1,"Claude Opus 4.8":2,"UNICO/NOUS: Claude (Fable 5":2,"mini-SWE-agent":3},"contributors":["AIBuildAI","Saivineeth147","srijanpatel","Humanize2 flame chase: GPT-5.6-sol + Claude Opus 5","Claude Opus 4.7 + GPT-5.5 (human-in-the-loop)","Claude Opus 4.7, 4.8 and Fable 5 + OSS contributions","Claude Opus 4.8 + Fable 5 (multi-agent)","UNICO/NOUS: Claude (Fable 5 + Opus 4.8) + GPT-5.6-Sol","daouid","rkirov","jzuiddam","KitaKen1","Solarys431","adamtopaz","homeowmorphism","ianklatzco","ldct","rigwild","will1491","yf225","Michael Johnson (MJ)","Actava","My Team","Claude Opus 4.6","Claude Sonnet 4.6","Claude Haiku 4.5","QDA","SethTS"],"highConfidence":59},{"family":"openai","records":90,"currentBests":5,"uncontestedBests":1,"competitions":[{"id":"mle-bench","name":"MLE-bench","records":20,"bests":0},{"id":"sokoban-speedrun","name":"Sokoban Speedrun","records":3,"bests":0},{"id":"lean-eval","name":"LeanEval","records":24,"bests":0},{"id":"alpaca-eval","name":"AlpacaEval","records":6,"bests":1},{"id":"chi-bench","name":"CHI-Bench","records":13,"bests":0},{"id":"programbench","name":"ProgramBench","records":6,"bests":1},{"id":"sutro-problems","name":"Sutro Problems","records":18,"bests":3}],"models":{"gpt-5-codex":4,"gpt-5":4,"o3":4,"gpt-4o-2024-08-06":8,"GPT 5.6 sol":3,"Codex packaging":1,"reviewer":1,"Aristotle":1,"GPT-5.6":4,"ChatGPT 5.6 Sol":2,"GPT-5.6 Sol)":2,"HITL":2,"savarin-6-hour-gpt-5.6-speedrun":1,"GPT-5.5":2,"deepseek-v4 and gpt-5.x":1,"mostly ChatGPT 5.6 Sol":1,"GPT-5.6 Sol":1,"OpenAI Codex (GPT-5.6 Sol)":1,"GPT-5.6 (human-in-the-loop)":1,"Codex (with human in the loop)":1,"gpt-4":3,"gpt-4-turbo":3,"openai/gpt-5.6-sol":4,"openai/gpt-5.6-luna":4,"openai/gpt-5.6-terra":4,"openai/gpt-5.5":1,"GPT-5.5 (xhigh reasoning)":1,"GPT-5.5 (high reasoning)":1,"GPT-5.4":1,"GPT-5.4 mini":1,"GPT-5 mini":1},"tools":{"Codex":21,"Humanifa":3,"Public accepted source":1,"Humanize RLCR: GPT-5.6-sol (max) worker":1,"GPT-5 Codex":1,"DeepScientist":2,"BRILLiant":2,"OpenAI Codex (GPT-6":2,"Codex 5.6 Sol":2,"mini-SWE-agent":6},"contributors":["Thesis","Operand ensemble","AIRA-dojo","OpenHands","MLAB","dexhunter","Humanifa + GPT 5.6 sol","Public accepted source + Codex packaging","Humanize RLCR: GPT-5.6-sol (max) worker + reviewer","GPT-5 Codex + Aristotle","DeepScientist + GPT-5.6","BRILLiant + ChatGPT 5.6 Sol","OpenAI Codex (GPT-6 + GPT-5.6 Sol)","Codex 5.6 Sol + HITL","ZhengyangZhang06","Morgan-Griffiths","savarin","juihuichung","A-M-Berns","eohjelle","ivwumupy","mccorvie","n-yamaguchi-0729","Cond-t","kimihiro64","LexBrill","LikC1606","lixiang90","matthewjasper","plby","alpaca_eval_gpt4","alpaca_eval_cot_gpt4_turbo_fn","alpaca_eval_gpt4_turbo_fn","alpaca_farm_greedy_gpt4","alpaca_eval_cot_gpt4_turbo_fn (low cost)","lmsys_gpt4","Actava","MedArise","GPT-5.5 (xhigh reasoning)","GPT-5.5 (high reasoning)","GPT-5.5","GPT-5.4","GPT-5.4 mini","GPT-5 mini","H32 MLP","512-unit MLP (96% target)","PCA-QDA","Reversible MLP, smaller workspace (12% error target)","32-unit MLP","1NN","Ordered ConvNets (3% error target)","Three ConvNets","512-unit MLP","cosminscn","sjbaebae"],"highConfidence":72},{"family":"other-ai","records":53,"currentBests":5,"uncontestedBests":0,"competitions":[{"id":"mle-bench","name":"MLE-bench","records":8,"bests":4},{"id":"lean-eval","name":"LeanEval","records":15,"bests":0},{"id":"swe-bench-pro-leaderboard","name":"SWE-bench Pro Leaderboard","records":1,"bests":0},{"id":"terminal-bench-leaderboard","name":"Terminal Bench 2.0 Leaderboard","records":7,"bests":1},{"id":"chi-bench","name":"CHI-Bench","records":12,"bests":0},{"id":"llm-leaderboard","name":"LLM-Leaderboard","records":10,"bests":0}],"models":{"Ensemble":4,"Tau (caj.al)":1,"Stealth Model":1,"Aleph Prover(logicalintelligence.com)":2,"github.com/mlgraham (various models)":1,"MerLean-Prover":1,"EVO (deepthought.com.au)":1,"Forge":1,"EVO":1,"Forall (Astrio)":1,"Various models ( with human in the loop )":1,"Leanstral 1.4":1,"Community multi-model project":1,"Autoform-Bot":1,"Trellis":1,"Green Agent":7,"MedGuard":4,"thinkingmachines/Inkling:peft:262144":4,"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144":4,"pythia-7b":5,"pythia-12b":5},"tools":{"NEO":4},"contributors":["Neo multi-agent","Disarray","lukerj00","rishistyping","mayorov-m-a","mlgraham","doxtor6","test1-deepthought","xiaoyangliu-sjtu","antpavzhi","machinelearning2014","nolanlwin","yawara","albertqjiang","mrdouglasny","niketp03","wpegden","AgentX-Spring0123","019d76c4-59a1-70f3-a147-643ce7091b40","019dd8de-40f9-74c3-ae33-91a250850feb","cuilinke","Actava","eleuther-pythia-7b","eleuther-pythia-12b"],"highConfidence":53},{"family":"meta","records":5,"currentBests":1,"uncontestedBests":0,"competitions":[{"id":"alpaca-eval","name":"AlpacaEval","records":4,"bests":0},{"id":"llm-leaderboard","name":"LLM-Leaderboard","records":1,"bests":1}],"models":{"llama-65b":1,"llama-13b":1,"llama-7b":1,"llama3-70b":1,"galactica-120b":1},"tools":{},"contributors":["guanaco-65b","vicuna-13b","alpaca-7b","alpaca_eval_llama3_70b_fn","gal-120b"],"highConfidence":5},{"family":"axiom","records":1,"currentBests":1,"uncontestedBests":0,"competitions":[{"id":"lean-eval","name":"LeanEval","records":1,"bests":1}],"models":{"Axiom Prover (Axiom Math)":1},"tools":{},"contributors":["Vilin97"],"highConfidence":1},{"family":"google","records":45,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"mle-bench","name":"MLE-bench","records":44,"bests":0},{"id":"programbench","name":"ProgramBench","records":1,"bests":0}],"models":{"Gemini-3-Pro-Preview":28,"Gemini-2.5-Pro":12,"Gemini-3-Flash-Preview":4,"Gemini 3 Flash":1},"tools":{"mini-SWE-agent":1},"contributors":["Famou-Agent 2.0","CAIR MARS+","MLEvolve","PiEvolve (24h)","CAIR MARS","PiEvolve (12h)","Leeroo","CAIR MLE-STAR-Pro-1.5","Famou-Agent","CAIR MLE-STAR-Pro-1.0","LoongFlow","Gemini 3 Flash"],"highConfidence":45},{"family":"deepseek","records":14,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"mle-bench","name":"MLE-bench","records":12,"bests":0},{"id":"lean-eval","name":"LeanEval","records":2,"bests":0}],"models":{"Deepseek-V3.2-Speciale":4,"deepseek-r1":8,"DeepSeek V4":2},"tools":{"NEAR AI":2},"contributors":["ML-Master 2.0","InternAgent","ML-Master","NEAR AI w/ DeepSeek V4","skidanovalex"],"highConfidence":14},{"family":"harmonic","records":7,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"lean-eval","name":"LeanEval","records":7,"bests":0}],"models":{"Aristotle (Harmonic)":7},"tools":{},"contributors":["LorenzoLuccioli","parabamoghv","sqrt-of-2","JohnEdwardJennings","kim-em","adrianmartir","Parcly-Taxel"],"highConfidence":7},{"family":"moonshot","records":4,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"chi-bench","name":"CHI-Bench","records":4,"bests":0}],"models":{"moonshotai/kimi-k3":4},"tools":{},"contributors":["Actava"],"highConfidence":4},{"family":"zhipu","records":4,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"chi-bench","name":"CHI-Bench","records":4,"bests":0}],"models":{"z-ai/glm-5.2":4},"tools":{},"contributors":["Actava"],"highConfidence":4},{"family":"bytedance","records":2,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"lean-eval","name":"LeanEval","records":2,"bests":0}],"models":{"Seed Prover (ByteDance)":2},"tools":{},"contributors":["GanjinZero","hanwenzhu"],"highConfidence":2},{"family":"xai","records":1,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"lean-eval","name":"LeanEval","records":1,"bests":0}],"models":{"Grok 4.5":1},"tools":{},"contributors":["rwst"],"highConfidence":1},{"family":"human","records":1,"currentBests":0,"uncontestedBests":0,"competitions":[{"id":"alpaca-eval","name":"AlpacaEval","records":1,"bests":0}],"models":{},"tools":{},"contributors":["humans"],"highConfidence":1}]