Compare / Gemini 3.1 Pro Preview vs Gemini 3.7 Flash

Gemini 3.1 Pro Preview vs Gemini 3.7 Flash

14 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Gemini 3.1 Pro Preview
Google · profile
Gemini 3.7 Flash
Google · profile
Results compared
14
Shared sources
2
BenchmarkMetricGemini 3.1 Pro PreviewGemini 3.7 Flash
Arena (formerly LMArena)reportedConfirmed task successIPS effect estimate -0.080.00
Arena (formerly LMArena)reportedPraise over complaintIPS effect estimate -0.01-0.03
Arena (formerly LMArena)reportedSteerabilityIPS effect estimate -0.04-0.00
Arena (formerly LMArena)reportedTool groundingIPS effect estimate -0.00-0.00
Arena (formerly LMArena)reportedOverallArena rating 1,4721,477
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4771,483
Arena (formerly LMArena)reportedCreative writingArena rating 1,4801,492
Arena (formerly LMArena)reportedExpert promptsArena rating 1,5091,512
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4791,487
Arena (formerly LMArena)reportedOverallArena rating 1,4871,488
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4801,496
UGI LeaderboardreportedRequested-length error% off the requested word count 19.0%7.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.340.33
UGI LeaderboardreportedWriting scorescore out of 100 72.277.5

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.