Every AI leaderboard

28 leaderboards · 989 models ranked

Breezeblue vs Microsoft vs DeepSeek vs ElevenLabs

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.

  • Breezeblue
  • Microsoft
  • DeepSeek
  • ElevenLabs

Head to head on 4 boards: DeepSeek places best on 2, Microsoft places best on 1, ElevenLabs places best on 1 and Breezeblue places best on 0. All 4 ranked on 0 of 21 boards.

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

BoardBreezeblueMicrosoftDeepSeekElevenLabs
Chat2
MultiChallengeScoretoday#574.9%DeepSeek V4P1 Flash
Text ArenaArena ratingtoday#321,475DeepSeek V4.1 Flash
Reasoning6
MMLU-ProAccuracy · staletoday#7576.0%Phi 4 Plus#3385.0%best of the pickedDeepSeek-V3.2
LiveBenchGlobal averagetoday#881.1%DeepSeek V4.1 Flash
AA IntelligenceIndextoday#1732.6DeepSeek V4.1 Flash
ARC-AGI-2Scoretoday#2078.1%DeepSeek V4.1 Flash
Epoch ECIECItoday#21159.3DeepSeek V4.1 Flash
GPQA DiamondAccuracytoday#2293.2%DeepSeek V4.1 Flash
Coding3
Aider PolyglotPass rate · staletoday#874.2%DeepSeek-V3.2
SWE-bench VerifiedResolved · staletoday#1170.0%DeepSeek-V3.2
WebDev ArenaArena ratingtoday#141,664DeepSeek V4.1 Flash
Agents and tools1
BFCLOverall accuracy · staletoday#5028.8%Phi 4#1256.7%best of the pickedDeepSeek-V3.2
Vision1
Vision ArenaArena ratingtoday#351,263DeepSeek V4.1 Flash
Image2
Image EditArena ratingtoday#41,468MAI Image 2.7
Text-to-ImageArena ratingtoday#61,329MAI Image 2.6
Speech2
Speech ArenaArena ratingtoday#131,228Breeze TTS 2#311,144Azure Hd 2.5#11,338best of the pickedEleven V4
Open ASRAverage WERtoday#35.55 WERbest of the pickedazure-speech-09-2026 (microsoft)#55.93 WERscribe v2 (elevenlabs)
Embeddings1
MTEBMean task scoretoday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtoday#1323 tok/sDeepSeek V4 Pro 0813
Price1
AA PriceBlended pricetoday#4$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokenstoday#155.4T tokDeepSeek 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