Compare / Mistral Small 3.2 24B vs GLM 4.6

Mistral Small 3.2 24B vs GLM 4.6

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

Mistral Small 3.2 24B
Mistral · profile
GLM 4.6
Z.ai · profile
Results compared
17
Shared sources
3
BenchmarkMetricMistral Small 3.2 24BGLM 4.6
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3631,412
Arena (formerly LMArena)reportedCreative writingArena rating 1,3231,400
Arena (formerly LMArena)reportedExpert promptsArena rating 1,3351,439
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3381,412
Arena (formerly LMArena)reportedOverallArena rating 1,3571,424
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3291,405
Berkeley Function Calling Leaderboard (BFCL) V4reportedIrrelevance detection% correct 87.9%85.0%
Berkeley Function Calling Leaderboard (BFCL) V4reportedMemory% correct 18.1%55.7%
Berkeley Function Calling Leaderboard (BFCL) V4reportedMulti-turn tasks% correct 14.8%68.0%
Berkeley Function Calling Leaderboard (BFCL) V4reportedOverall accuracy% correct 37.1%72.4%
Berkeley Function Calling Leaderboard (BFCL) V4reportedRelevance detection% correct 93.8%75.0%
Berkeley Function Calling Leaderboard (BFCL) V4reportedSingle-turn calls (curated)% correct 89.7%87.6%
Berkeley Function Calling Leaderboard (BFCL) V4reportedSingle-turn calls (user-contributed)% correct 79.0%80.9%
Berkeley Function Calling Leaderboard (BFCL) V4reportedWeb search% correct 31.0%77.5%
UGI LeaderboardreportedRequested-length error% off the requested word count 17.0%13.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.350.38
UGI LeaderboardreportedWriting scorescore out of 100 36.353.3

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.