Mistral Small (Sep '24)

open weightsdeprecated by benchmark source

Mistral · released 2024-09-17 · 0 offers

Context 33K tokens

Providers

No provider publishes an API price for this model yet, so no cost can be modeled.

1 of 7 inputs6 radar axes: DesignArena's two boards share one

1.7

Thin data · 1/7

AA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 2.3AA Agentic —Epoch ECI —Software ECI —DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

7 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Humanity's Last Exam (AA text-only)184.3%2026-09-10
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
UGI NatInt4025.12026-09-10
UGI NatInt published 2026-09-10 → · Published board — A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics.

Japanese-RP-Bench (Aratako)03.752026-09-10
Japanese-RP-Bench (Aratako) published 2026-09-10 → · Published board — Benchmark measuring LLM Japanese roleplay ability via 10-turn two-model dialogues scored by a four-judge ensemble across eight criteria.

GPQA Diamond (AA)1338.1%2026-09-10
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.

UGI Willingness785.002026-09-10
UGI Willingness published 2026-09-10 → · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI5234.62026-09-10
UGI published 2026-09-10 → · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.

UGI Writing4432.62026-09-10
UGI Writing published 2026-09-10 → · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.

Missing coverage · 312 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.