Every AI leaderboard

28 leaderboards · 986 models ranked

MiniMax vs Microsoft vs Anthropic vs DeepSeek

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.

  • MiniMax
  • Microsoft
  • Anthropic
  • DeepSeek

Head to head on 19 boards: Anthropic places best on 15, DeepSeek places best on 3, MiniMax places best on 1 and Microsoft places best on 0. All 4 ranked on 1 of 28 boards.

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

BoardMiniMaxMicrosoftAnthropicDeepSeek
Chat2
Text ArenaArena ratingtoday#41,505best of the pickedClaude Opus 5.5#321,475DeepSeek V4.1 Flash
MultiChallengeScoretoday#1067.7%Claude Haiku 5.5#574.9%best of the pickedDeepSeek V4P1 Flash
Reasoning7
MMLU-ProAccuracy · staletoday#688.0%MiniMax M2.1#7576.0%Phi 4 Plus#489.1%best of the pickedClaude Opus 4.6#3385.0%DeepSeek-V3.2
LiveBenchGlobal averagetoday#5967.3%MiniMax-M3#183.4%best of the pickedClaude Fable 5.1#881.1%DeepSeek V4.1 Flash
AA IntelligenceIndextoday#2229.1MiniMax-M3.1-Flash#259.1best of the pickedClaude Opus 5.5#1632.6DeepSeek V4.1 Flash
GPQA DiamondAccuracytoday#3490.9%MiniMax-M3#395.6%best of the pickedClaude Sonnet 5.5#2193.2%DeepSeek V4.1 Flash
Epoch ECIECItoday#72147.6MiniMax-M3#3168.4best of the pickedClaude Opus 5.5#19159.3DeepSeek V4.1 Flash
ARC-AGI-2Scoretoday#644.9%MiniMax-M2.5#393.3%best of the pickedClaude Opus 5.5#1978.1%DeepSeek V4.1 Flash
HLEAccuracytoday#246.5%Claude Fable 5.1
Coding4
WebDev ArenaArena ratingtoday#341,582MiniMax-M3.1-Flash#11,814best of the pickedClaude Opus 5.5#141,665DeepSeek V4.1 Flash
SWE-bench VerifiedResolved · staletoday#275.8%MiniMax-M2.5#176.8%best of the pickedClaude Opus 4.5#1170.0%DeepSeek-V3.2
SWE-Bench ProResolvedtoday#1084.3%MiniMax M3P1 Flash#198.0%best of the pickedClaude Opus 5
Aider PolyglotPass rate · staletoday#1072.0%Claude Opus 4#874.2%best of the pickedDeepSeek-V3.2
Agents and tools3
BFCLOverall accuracy · staletoday#5028.8%Phi 4#177.5%best of the pickedClaude Opus 4.5#1256.7%DeepSeek-V3.2
MCP AtlasPass ratetoday#387.2%Claude Fable 5.1
Search ArenaArena ratingtoday#51,229Claude Fable 5
Vision2
Vision ArenaArena ratingtoday#611,231MiniMax-M3#11,309best of the pickedClaude Fable 5#341,263DeepSeek V4.1 Flash
Document ArenaArena ratingtoday#351,435MiniMax-M3#11,499best of the pickedClaude Fable 5
Image2
Image EditArena ratingtoday#41,467MAI Image 2.7
Text-to-ImageArena ratingtoday#61,330MAI Image 2.6
Video2
Image-to-VideoArena ratingtoday#21,493MiniMax H3
Text-to-VideoArena ratingtoday#111,457MiniMax H3
Speech2
Speech ArenaArena ratingtoday#271,175best of the pickedSpeech 2.8 Hd#311,145Azure Hd 2.5
Open ASRAverage WERtoday#35.55 WERazure-speech-09-2026 (microsoft)
Embeddings1
MTEBMean task scoretoday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtoday#1717 tok/sMiniMax-M3.1-Flash#931 tok/sbest of the pickedClaude Sonnet 5.5#1323 tok/sDeepSeek V4 Pro 0813
Price1
AA PriceBlended pricetoday#1$0.20best of the pickedClaude Haiku 5.5#3$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokenstoday#75.0T tokMiniMax-M3.1-Flash#66.8T tokClaude Opus 5.5#156.0T tokbest of the pickedDeepSeek V4.1 Flash

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