Model record

Mistral Medium 3.5

Open weights

Mistral AI · released Apr 28, 2026

Overall standing

Overall
40.2rank 49 of 62
40.2 is at approximately the 22th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 48.9.
8 of 8 measured
Category standingsReasoning 54.4Coding 45.1Math 0.0Agentic 14.4
Reasoning
54.4rank 51 of 62
54.4 is at approximately the 19th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 64.8.
4 of 4 measured
Coding
45.1rank 36 of 46
45.1 is at approximately the 23th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 56.1.
2 of 2 measured
Math
0.0rank 53 of 62
0.0 is at approximately the 8th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.3.
1 of 1 measured
Agentic
14.4rank 31 of 46
14.4 is at approximately the 34th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.6.
1 of 1 measured
Model factsOpen weights · $1.5 / $7.5 per 1M

Copied from the linked provider page; no separate retrieval date is stored.

Provider
Mistral AI
Released
Weights
Open weights
Context window
262,144 tokens
Input price / Mtok
$1.5
Output price / Mtok
$7.5
Reasoning effort
Not listed

Scores and sources

Measured scores retain their source and retrieval date. Missing scores are not treated as zero.

Benchmark scores, evaluation settings, sources, and retrieval dates for Mistral Medium 3.5
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding50.6Artificial Analysis independent run; 89 tasks; Terminus 2 on E2B; 3 repeats; pass@1; 250-episode cap; 2-hour timeoutOpen source (opens in a new tab)
τ³-BankingAgentic14.4Artificial Analysis independent run; 97 tasks; 5 repeats; backend-state pass@1; BM25 plus grep retrieval; 200-step capOpen source (opens in a new tab)
AA-LCRReasoning61.0Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no toolsOpen source (opens in a new tab)
Humanity's Last ExamReasoning12.8Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no toolsOpen source (opens in a new tab)
GPQA DiamondReasoning74.9Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding39.6Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning68.8Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath0.0Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no toolsOpen source (opens in a new tab)