Skip to content

Intfloat vs Google

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.

  • Intfloat
  • Google

Head to head on 1 board: Google places best on 1 and Intfloat places best on 0. Both ranked on 1 of 28 boards.

BoardIntfloatGoogle
Chat2
Text ArenaArena ratingtoday#11,525Gemini 4 Argon
MultiChallengeScoretoday#371.4%Gemini 3.1 Pro Preview
Reasoning7
MMLU-ProAccuracy · staletoday#191.2%Gemini 3.1 Pro Preview
HLEAccuracytoday#346.4%Gemini 3.1 Pro Preview
GPQA DiamondAccuracytoday#395.4%Gemini 3.8 Flash
AA IntelligenceIndextoday#552.6Gemini 4 Argon
ARC-AGI-2Scoretoday#889.2%Gemini 3.8 Flash
Epoch ECIECItoday#14157.4Gemini 3.7 Flash
LiveBenchGlobal averagetoday#1478.8%Gemini 3.7 Flash
Coding4
SWE-bench VerifiedResolved · staletoday#275.8%Gemini 3 Flash
Aider PolyglotPass rate · staletoday#383.1%Gemini 2.5 Pro (Jun 2025)
WebDev ArenaArena ratingtoday#81,680Gemini 4 Argon
SWE-Bench ProResolvedtoday#958.8%Gemini 3.8 Flash
Agents and tools3
BFCLOverall accuracytoday#372.5%Gemini 3 Pro
MCP AtlasPass ratetoday#683.6%Gemini 3.5 Flash
Search ArenaArena ratingtoday#91,210Gemini 3.1 Pro Grounding
Vision2
Vision ArenaArena ratingtoday#51,296Gemini 3.7 Flash
Document ArenaArena ratingtoday#161,463Gemini 3.5 Flash
Image2
Text-to-ImageArena ratingtoday#91,261Gemini 3.1 Flash Image
Image EditArena ratingtoday#101,390Gemini 3 Pro Image
Video2
Text-to-VideoArena ratingtoday#11,516Gemini Omni 1.1 Flash
Image-to-VideoArena ratingtoday#21,488Gemini Omni 1.1 Flash
Speech2
Speech ArenaArena ratingtoday#41,275Gemini 3.8 Flash TTS
Open ASRAverage WERtoday#619.51 WERgemma-4-E4B-it (google)
Embeddings1
MTEBMean task scoretoday#2563.2%multilingual-e5-large-instruct (intfloat)#568.4%best of the pickedgemini-embedding-001 (google)
Speed1
AA SpeedOutput speedtoday#1249 tok/sGemini 3.8 Flash
Price1
AA PriceBlended pricetoday#10$1.50Gemini 3.8 Flash
Usage1
OpenRouterWeekly tokenstoday#132.2T tokGemini 3.8 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

New #1s by email

Saturdays, only in weeks when a leaderboard has a new #1.

Double opt-in. Unsubscribe any time.