Every AI leaderboard

Leaderboards28Models ranked986

28 leaderboards · 986 models ranked

DeepSeek vs Anthropic vs OpenAI vs Microsoft

Each lab shows its best-ranked model on every board. One row per board where at least one is ranked, from each board's current capture.

  • DeepSeek
  • Anthropic
  • OpenAI
  • Microsoft

Head to head on 25 boards: Anthropic places best on 12, OpenAI places best on 10, Microsoft places best on 2 and DeepSeek places best on 1. All 4 ranked on 2 of 27 boards.

Two at a time on this screen. Tap one to swap it in.

BoardDeepSeekAnthropicOpenAIMicrosoft
Chat2
MultiChallengeScoretoday#574.9%DeepSeek V4P1 Flash#1067.7%Claude Haiku 5.5#182.0%best of the pickedGPT-6.1 Sol
Text ArenaArena ratingtoday#321,475DeepSeek V4.1 Flash#41,505best of the pickedClaude Opus 5.5#191,485GPT-5.6 Sol
Reasoning7
MMLU-ProAccuracy · staletoday#3385.0%DeepSeek-V3.2#489.1%Claude Opus 4.6#389.3%best of the pickedo1#7576.0%Phi 4 Plus
Epoch ECIECItoday#19159.3DeepSeek V4.1 Flash#3168.4Claude Opus 5.5#1169.1best of the pickedGPT-6 Astra
ARC-AGI-2Scoretoday#1978.1%DeepSeek V4.1 Flash#393.3%Claude Opus 5.5#195.0%best of the pickedGPT-6 Astra
LiveBenchGlobal averagetoday#881.1%DeepSeek V4.1 Flash#183.4%best of the pickedClaude Fable 5.1#482.2%GPT-6 Astra
AA IntelligenceIndextoday#1632.6DeepSeek V4.1 Flash#259.1best of the pickedClaude Opus 5.5#356.9GPT-6 Astra
GPQA DiamondAccuracytoday#2193.2%DeepSeek V4.1 Flash#395.6%Claude Sonnet 5.5#295.8%best of the pickedGPT-6 Astra
HLEAccuracytoday#246.5%Claude Fable 5.1#154.8%best of the pickedGPT-6 Astra
Coding4
WebDev ArenaArena ratingtoday#141,665DeepSeek V4.1 Flash#11,814best of the pickedClaude Opus 5.5#31,770GPT-6 Astra
SWE-bench VerifiedResolved · staletoday#1170.0%DeepSeek-V3.2#176.8%best of the pickedClaude Opus 4.5#672.8%GPT-5.2
Aider PolyglotPass rate · staletoday#874.2%DeepSeek-V3.2#1072.0%Claude Opus 4#188.0%best of the pickedGPT-5
SWE-Bench ProResolvedtoday#198.0%best of the pickedClaude Opus 5#490.2%GPT-6 Astra
Agents and tools3
BFCLOverall accuracy · staletoday#1256.7%DeepSeek-V3.2#177.5%best of the pickedClaude Opus 4.5#763.0%o3#5028.8%Phi 4
Search ArenaArena ratingtoday#51,229Claude Fable 5#11,255best of the pickedGPT-5.6 Sol
MCP AtlasPass ratetoday#387.2%best of the pickedClaude Fable 5.1#1481.8%GPT-5.6
Vision2
Vision ArenaArena ratingtoday#341,263DeepSeek V4.1 Flash#11,309best of the pickedClaude Fable 5#81,293GPT-6.1 Sol
Document ArenaArena ratingtoday#11,499best of the pickedClaude Fable 5#51,486GPT-5.6 Sol
Image2
Text-to-ImageArena ratingtoday#11,429best of the pickedGPT Image 2.5 Sunburst#61,330MAI Image 2.6
Image EditArena ratingtoday#11,517best of the pickedGPT Image 2.5 Sunburst#41,467MAI Image 2.7
Video1
Text-to-VideoArena ratingtoday#131,367Sora 2 Pro
Speech2
Open ASRAverage WERtoday#186.80 WERgpt-transcribe (openai)#35.55 WERbest of the pickedazure-speech-09-2026 (microsoft)
Speech ArenaArena ratingtoday#421,107TTS 1 Hd#311,145best of the pickedAzure Hd 2.5
Embeddings1
MTEBMean task scoretoday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtoday#1323 tok/sDeepSeek V4 Pro 0813#931 tok/sbest of the pickedClaude Sonnet 5.5#1522 tok/sGPT-6.1 Sol
Price1
AA PriceBlended pricetoday#3$0.53DeepSeek V4.1 Flash#1$0.20best of the pickedClaude Haiku 5.5#6$2.00GPT-6.1 Terra
Usage1
OpenRouterWeekly tokenstoday#156.0T tokbest of the pickedDeepSeek V4.1 Flash#66.8T tokClaude Opus 5.5#47.2T tokGPT-6 Luna

Green marks the best placing among the picked where two or more are ranked; ties are marked for each. Ranks are each board's own order (lower is better), scores as the board published them. Dash: not on that board.

More comparisons