Compare / Nova 2 Lite vs Gemini 2.5 Flash

Nova 2 Lite vs Gemini 2.5 Flash

17 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Nova 2 Lite
Amazon · profile
Gemini 2.5 Flash
Google · profile
Results compared
17
Shared sources
3
BenchmarkMetricNova 2 LiteGemini 2.5 Flash
Arena (formerly LMArena)reportedOverallArena rating 1,3801,437
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3511,399
Arena (formerly LMArena)reportedCreative writingArena rating 1,2691,394
Arena (formerly LMArena)reportedExpert promptsArena rating 1,3541,424
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3271,400
Arena (formerly LMArena)reportedOverallArena rating 1,3351,409
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,2981,402
Berkeley Function Calling Leaderboard (BFCL) V4reportedIrrelevance detection% correct 82.1%93.7%
Berkeley Function Calling Leaderboard (BFCL) V4reportedMemory% correct 2.4%41.3%
Berkeley Function Calling Leaderboard (BFCL) V4reportedMulti-turn tasks% correct 2.1%36.2%
Berkeley Function Calling Leaderboard (BFCL) V4reportedOverall accuracy% correct 27.1%56.2%
Berkeley Function Calling Leaderboard (BFCL) V4reportedRelevance detection% correct 75.0%75.0%
Berkeley Function Calling Leaderboard (BFCL) V4reportedSingle-turn calls (curated)% correct 87.0%88.1%
Berkeley Function Calling Leaderboard (BFCL) V4reportedSingle-turn calls (user-contributed)% correct 80.8%78.2%
Berkeley Function Calling Leaderboard (BFCL) V4reportedWeb search% correct 5.0%62.0%
Vectara Hallucination LeaderboardreportedAnswer rate% of documents 99.6%99.0%
Vectara Hallucination LeaderboardreportedHallucination rate% of summaries 5.1%7.8%

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.