Every board we track
29 AI leaderboards, who is #1 on each, and when each one last published.
Text Arena
LMArena
1
Claude Fable 51,506
2
Claude Opus 4.61,505
3
Claude Opus 4.71,502
Published Sep 13, 2026100 models
MultiChallenge
Scale AI
1
Muse Spark75.5%
2
Muse Spark 1.175.3%
3
Gemini 3.1 Pro Preview71.4%
Published Sep 24, 202629 models
AA Intelligence
Artificial Analysis
1
Claude Opus 5.557.6
2
Claude Fable 5.153.4
3
GPT-6 Astra52.7
Published Sep 24, 2026100 models
HLE
Scale AI and CAIS
1
GPT-6 Astra54.8%
2
Claude Fable 5.146.5%
3
Gemini 3.1 Pro Preview46.4%
Published Sep 24, 202642 models
GPQA Diamond
Epoch AI
1
GPT-6 Astra95.8%
2
Gemini 3.8 Flash95.4%
3
Gemini 3.7 Flash94.8%
Published Sep 2, 2026100 models
Epoch ECI
Epoch AI
1
GPT-6 Astra166.6
2
Claude Fable 5.1165.0
3
Claude Fable 5163.6
Published Sep 24, 2026100 models
ARC-AGI-2
ARC Prize
1
GPT-6 Astra95.0%
2
Claude Opus 5.593.3%
3
GPT-5.6 Sol92.5%
Published Sep 22, 202678 models
LiveBench
LiveBench
1
Claude Fable 5.183.4%
2
Claude Opus 5.583.2%
3
Claude Fable 583.0%
Published Jun 25, 202659 models
MMLU-Pro
TIGER-Lab
1
Gemini 3.1 Pro Preview91.2%
2
Gemini 3 Pro90.1%
3
o189.3%
Stale since 2026-03-11100 models
WebDev Arena
LMArena
1
Claude Opus 5.51,818
2
GPT-6 Astra1,792
3
Claude Fable 5.11,755
Published Sep 23, 2026100 models
SWE-Bench Pro
Scale AI
1
Claude Opus 598.0%
2
Claude Fable 5.192.2%
3
GPT-6 Astra90.2%
Published Sep 24, 202611 models
SWE-bench Verified
SWE-bench
1
Claude Opus 4.576.8%
2
Gemini 3 Flash75.8%
2
MiniMax-M2.575.8%
Stale since 2026-02-2639 models
Aider Polyglot
Aider
1
GPT-588.0%
2
o3-pro84.9%
3
Gemini 2.5 Pro (Jun 2025)83.1%
Stale since 2025-10-0350 models
BFCL
UC Berkeley Gorilla
1
Claude Opus 4.577.5%
2
Claude Sonnet 4.573.2%
3
Gemini 3 Pro72.5%
Published Apr 12, 202681 models
MCP Atlas
Scale AI
1
Muse Spark 1.188.1%
2
Claude Fable 5.187.2%
3
Claude Opus 585.8%
Published Sep 23, 202634 models
Search Arena
LMArena
1
GPT-5.6 Sol1,257
2
Claude Opus 4.61,253
3
GPT-5.51,242
Published Aug 24, 202633 models
Vision Arena
LMArena
1
Claude Fable 51,310
2
Qwen3.8 Max (0902)1,302
3
Claude Opus 4.71,301
Published Sep 13, 2026100 models
Document Arena
LMArena
1
Claude Opus 51,516
2
Claude Fable 5.11,513
3
Claude Opus 4.61,507
Published Sep 13, 202638 models
Text-to-Image
LMArena
1
GPT Image 2.5 Sunburst1,423
2
GPT Image 2.5 Flare1,401
3
GPT Image 21,381
Published Sep 21, 202675 models
Image Edit
LMArena
1
GPT Image 2.5 Sunburst1,526
2
GPT Image 2.5 Flare1,482
3
GPT Image 21,461
Published Sep 21, 202653 models
Text-to-Video
LMArena
1
Gemini Omni 1.1 Flash1,516
2
Gemini Omni Flash1,513
3
Flux 3 Video1,493
Published Sep 21, 202648 models
Image-to-Video
LMArena
1
MiniMax H31,495
2
Gemini Omni 1.1 Flash1,488
3
Wan3.01,480
Published Sep 21, 202648 models
Speech Arena
Artificial Analysis
1
Sonic 3.61,273
2
Gemini 3.8 Flash TTS1,260
3
Qwen Audio 3.0 TTS Plus1,259
Published Sep 24, 202691 models
Open ASR
Hugging Face
1scribe v2 pro (zoom)3.59 WER
2
azure-speech-07-2026 (microsoft)3.81 WER
3multilingual (modulate)3.84 WER
Published Sep 22, 202667 models
MTEB
MTEB
1
harrier-oss-v1-27b (microsoft)74.3%
2
KaLM-Embedding-Gemma3-12B-2511 (tencent)72.3%
3
llama-embed-nemotron-8b (nvidia)69.5%
Published Sep 22, 202688 models
AA Speed
Artificial Analysis
1
Gemini 3.8 Flash291 tok/s
2
DeepSeek V4.1 Flash232 tok/s
3
Muse Spark 1.3228 tok/s
Published Sep 24, 202624 models
AA Price
Artificial Analysis
1Agnes 3.0 Flash$0.07
2Agnes 2.5 Pro Beta$0.15
3
GPT-6 Luna$0.20
Published Sep 24, 202627 models
OpenRouter
OpenRouter
1
GLM 5.3 Flash19.0T tok
2
DeepSeek V4.1 Flash18.4T tok
3
Hy4 preview13.0T tok
Published Sep 23, 202619 models
Open LLM LB
Hugging Face
Retired 2025-03-20. Listed for reference.
Retired
Scores as published by each board on the capture date. Model names and logos belong to their owners; logos via logo.dev.