Frontier Log

MistralModel

Mistral Small 4 119B

Made by
Mistral
Released
Announced in
Introducing Mistral Small 4mistral.ai
Event
Mistral Small 4
API record
/api/v1/models/mistral-small-4

Benchmark results

BenchmarkScoreSource check
GPQA Diamondreasoning mode71.2%
CheckedA person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
instruct mode, no reasoning59.1%
CheckedA person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
BrowseCompharness and context management not stated · reported later, in Remote agents in Vibe. Powered by Mistral Medium 3.5.21.3%
CheckedA person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.
Sources

Reported by Mistral

Events

All models