benchgap
Mistral · model

Mistral Medium 3 benchmark scores

As of 2026-11-22, Mistral Medium 3 (Mistral) has measured scores on 10 benchmarks and estimated scores on 51 more.

BenchmarkScoreSource
AA-GPQA Diamond57.8%measured
AA-HLE4.1%measured
AA-SciCode5.6%estimated ± 4.7 pp, medium confidence
Artificial Analysis Intelligence Index9.0%measured
CritPt0.0%measured
GDPval-AA0.0%estimated ± 11.0 pp, low confidence
GPQA Diamond68.7%estimated ± 2.4 pp, medium confidence
HLE16.7%estimated ± 8.5 pp, low confidence
IFBench54.1%estimated ± 6.6 pp, low confidence
AA-LCR31.3%measured
LiveCodeBench v630.3%measured
AA-Omniscience Accuracy18.3%measured
SciCode8.4%estimated ± 4.9 pp, medium confidence
BrowseComp30.4%estimated ± 13.0 pp, low confidence
IFEval88.6%estimated ± 2.8 pp, high confidence
LongBench v251.2%estimated ± 5.5 pp, medium confidence
τ²-bench results24.3%measured
AA Coding Index2.7%estimated ± 5.7 pp, low confidence
AA-MMMU-Pro53.0%measured
APEX-Agents-AA1.6%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
SWE-bench Verified57.5%estimated ± 9.7 pp, low confidence
BFCL v423.7%estimated ± 8.5 pp, low confidence
AA Agentic Index0.0%estimated ± 12.7 pp, low confidence
MMLU-Pro82.6%estimated ± 5.0 pp, medium confidence
AA-IFBench39.3%measured
GPQA61.3%estimated ± 6.1 pp, medium confidence
MMLU81.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond56.9%estimated ± 3.2 pp, high confidence
Vals MMLU-Pro76.5%estimated ± 2.9 pp, high confidence
MMMLU83.3%estimated ± 0.7 pp, medium confidence
MMMU67.5%estimated ± 2.7 pp, high confidence
AA MMLU-Pro83.8%estimated ± 0.8 pp, medium confidence
ARC-AGI-174.7%estimated ± 7.8 pp, low confidence
ARC-AGI-230.5%estimated ± 14.4 pp, low confidence
ParseBench-143.2%estimated ± 6.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)48.5%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)39.6%estimated ± 1.1 pp, low confidence
HLE w/o tools23.1%estimated ± 4.9 pp, high confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
ParseBench-238.8%estimated ± 6.2 pp, medium confidence
CharXiv64.9%estimated ± 6.3 pp, low confidence
AI2D_TEST88.0%estimated ± 2.0 pp, low confidence
C-Eval88.3%estimated ± 1.0 pp, low confidence
MMLU-Redux93.3%estimated ± 0.8 pp, low confidence
MMMU-Pro53.5%estimated ± 1.5 pp, high confidence
ScreenSpot Pro59.1%estimated ± 10.8 pp, low confidence
SuperGPQA64.6%estimated ± 9.3 pp, low confidence
Video-MME (w/o subtitle)72.2%estimated ± 1.7 pp, low confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low 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
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA15.8%estimated ± 4.3 pp, medium confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
MMLongBench-Doc56.5%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
MMMU-Pro w/ Python58.4%estimated ± 2.0 pp, medium confidence