Compare / Gemini 3.8 Flash vs GPT-5.1

Gemini 3.8 Flash vs GPT-5.1

19 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Gemini 3.8 Flash
Google · profile
GPT-5.1
OpenAI · profile
Results compared
19
Shared sources
5
BenchmarkMetricGemini 3.8 FlashGPT-5.1
Arena (formerly LMArena)reportedOverallArena rating 1,4771,459
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4821,448
Arena (formerly LMArena)reportedCreative writingArena rating 1,4821,428
Arena (formerly LMArena)reportedExpert promptsArena rating 1,5291,482
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4881,450
Arena (formerly LMArena)reportedOverallArena rating 1,4921,456
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4861,437
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 76.349.4
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 40.924.7
Artificial AnalysisreportedGPQA Diamond% of questions 95.3%87.3%
Artificial AnalysisreportedHumanity's Last Exam% of questions 47.8%28.5%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 84.0%80.0%
Artificial AnalysisreportedTerminal-Bench 2.1% of tasks 87.6%52.4%
Artificial AnalysisreportedΤ-bench banking% of tasks 45.8%15.9%
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 69.7%48.0%
UGI LeaderboardreportedRequested-length error% off the requested word count 13.0%113.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.340.38
UGI LeaderboardreportedWriting scorescore out of 100 78.555.8
Vending-Bench 2reportedMoney after a yearUS dollars $5,093.79$1,473.43

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.