Compare / Qwen3.5-122B-A10B vs Gemini 3.8 Flash

Qwen3.5-122B-A10B vs Gemini 3.8 Flash

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

Qwen3.5-122B-A10B
Alibaba · profile
Gemini 3.8 Flash
Google · profile
Results compared
19
Shared sources
3
BenchmarkMetricQwen3.5-122B-A10BGemini 3.8 Flash
Arena (formerly LMArena)reportedOverallArena rating 1,4281,477
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4221,482
Arena (formerly LMArena)reportedCreative writingArena rating 1,3661,482
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4421,529
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4061,488
Arena (formerly LMArena)reportedOverallArena rating 1,4161,492
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3871,486
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 45.776.3
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 17.740.9
Artificial AnalysisreportedGPQA Diamond% of questions 85.7%95.3%
Artificial AnalysisreportedHumanity's Last Exam% of questions 25.2%47.8%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 76.3%84.0%
Artificial AnalysisreportedSciCode% of problems 39.7%56.6%
Artificial AnalysisreportedTerminal-Bench 2.1% of tasks 47.6%87.6%
Artificial AnalysisreportedTerminal-Bench 4.0% of tasks 0.0%19.7%
Artificial AnalysisreportedΤ-bench banking% of tasks 15.3%45.8%
UGI LeaderboardreportedRequested-length error% off the requested word count 9.0%13.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.360.34
UGI LeaderboardreportedWriting scorescore out of 100 39.578.5

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.