benchgap
Mistral · model

Mistral Small 4 benchmark scores

As of 2026-11-22, Mistral Small 4 (Mistral) has measured scores on 13 benchmarks and estimated scores on 91 more.

BenchmarkScoreSource
AA-GPQA Diamond76.9%measured
AA-HLE9.9%measured
AA-SciCode38.8%measured
Artificial Analysis Intelligence Index4.3%measured
CritPt0.3%measured
GDPval-AA0.0%measured
GPQA Diamond73.4%estimated ± 2.4 pp, high confidence
HLE18.3%estimated ± 8.5 pp, medium confidence
IFBench55.5%estimated ± 6.6 pp, medium confidence
AA-LCR49.7%measured
LiveCodeBench v676.4%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy21.4%measured
SciCode39.0%estimated ± 3.1 pp, high confidence
BrowseComp13.3%estimated ± 9.0 pp, low confidence
HLE w/ tools33.8%estimated ± 5.3 pp, low confidence
IFEval90.8%estimated ± 2.8 pp, high confidence
LongBench v252.2%estimated ± 5.5 pp, medium confidence
τ²-bench results41.2%measured
AA Coding Index26.6%measured
AA-MMMU-Pro56.8%measured
APEX-Agents0.0%estimated ± 9.4 pp, low confidence
APEX-Agents-AA6.0%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)6.5%estimated ± 6.8 pp, low confidence
DeepSearchQA27.3%estimated ± 4.5 pp, medium confidence
SWE-bench Verified64.2%estimated ± 6.3 pp, medium confidence
BFCL v453.9%estimated ± 2.7 pp, high confidence
CyberGym46.7%estimated ± 5.3 pp, low confidence
JobBench0.0%estimated ± 8.7 pp, low confidence
SWE-bench Pro33.7%estimated ± 6.0 pp, medium confidence
WideResearch0.0%estimated ± 7.8 pp, low confidence
AA Agentic Index1.4%measured
MMLU-Pro84.2%estimated ± 5.0 pp, medium confidence
AA-IFBench48.2%measured
GPQA78.6%estimated ± 6.1 pp, medium confidence
MMLU89.7%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond76.0%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench75.7%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro79.9%estimated ± 2.9 pp, high confidence
MMMLU85.4%estimated ± 0.7 pp, medium confidence
MMMU70.5%estimated ± 2.7 pp, high confidence
AA MMLU-Pro84.3%estimated ± 0.8 pp, medium confidence
Gert Labs26.9%estimated ± 10.0 pp, low confidence
AA Harvey LAB v1.079.4%estimated ± 1.2 pp, low confidence
AA Tau3 Banking16.8%estimated ± 3.7 pp, medium confidence
ARC-AGI-175.0%estimated ± 7.8 pp, low confidence
ARC-AGI-231.1%estimated ± 14.4 pp, low confidence
CursorBench 3.235.8%estimated ± 5.3 pp, low confidence
FrontierCode 1.1 Main0.0%estimated ± 6.6 pp, low confidence
FrontierSWE v24.6%estimated ± 14.2 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
OSWorld-Verified55.4%estimated ± 8.4 pp, low confidence
ParseBench-144.6%estimated ± 6.2 pp, medium confidence
Vals SWE-bench50.6%estimated ± 5.5 pp, medium confidence
CWE-Bench-AA0.0%estimated ± 10.1 pp, low confidence
AA Cyber Index1.1%estimated ± 9.2 pp, low confidence
DeepsecBench-AA0.0%estimated ± 8.9 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)26.9%estimated ± 2.5 pp, low confidence
AA ITBench33.3%estimated ± 4.0 pp, medium confidence
Bug Hunt Bench13.8%estimated ± 10.5 pp, low confidence
CursorBench 4.025.5%estimated ± 4.9 pp, medium confidence
CWE-bench v10.0%estimated ± 6.4 pp, low confidence
DeepSWE28.4%estimated ± 7.5 pp, low confidence
DRACO0.0%estimated ± 2.0 pp, low confidence
FrontierCode 2.026.1%estimated ± 9.3 pp, low confidence
HLE w/o tools19.3%estimated ± 4.9 pp, medium confidence
PostTrainBench v1.125.3%estimated ± 7.4 pp, low confidence
Toolathlon-Verified5.6%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v468.4%estimated ± 6.8 pp, low confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Vibe Code Bench7.9%estimated ± 10.0 pp, low confidence
Hermes Bench0.0%estimated ± 2.9 pp, medium confidence
Hermes Index0.0%estimated ± 8.7 pp, low confidence
ParseBench-242.7%estimated ± 6.2 pp, medium confidence
CharXiv67.9%estimated ± 6.3 pp, low confidence
AI2D_TEST88.0%estimated ± 2.0 pp, medium confidence
C-Eval86.9%estimated ± 1.0 pp, low confidence
MCP Atlas64.6%estimated ± 7.8 pp, low confidence
MMLU-Redux93.7%estimated ± 0.8 pp, medium confidence
MMMU-Pro57.7%estimated ± 1.5 pp, high confidence
NL2Repo16.9%estimated ± 4.7 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
ScreenSpot Pro62.0%estimated ± 10.8 pp, low confidence
SuperGPQA64.9%estimated ± 9.3 pp, medium confidence
Toolathlon27.0%estimated ± 6.3 pp, low confidence
Video-MME (w/o subtitle)73.4%estimated ± 1.7 pp, medium confidence
AA LiveCodeBench84.0%estimated ± 4.7 pp, low confidence
HealthBench Hard3.5%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)78.3%estimated ± 4.0 pp, low confidence
React Native Evals70.8%estimated ± 3.2 pp, high confidence
ResearchClawBench2.8%estimated ± 1.9 pp, medium confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HLE-Verified16.6%estimated ± 7.1 pp, low confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA20.0%estimated ± 4.3 pp, medium confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, medium confidence
MRCRv222.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc59.4%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
MMMU-Pro w/ Python61.9%estimated ± 2.0 pp, medium confidence