Mistral Medium 3

Mistral Medium 3 is a non-reasoning model from Mistral. 13 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.30.5 ±7.0
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.35/s
Input / 1MUS dollars per 1M input tokens.$0.4
Output / 1MUS dollars per 1M output tokens.$2
ContextMaximum tokens in one request.131K
EloLMArena rating and rank.N/A

50 is the middle of the board. The range shows the doubt in the index.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
16.3
CodingCode writing and repair.
N/A
ReasoningLogic problems and puzzles.
34.1
MultimodalTasks with images and text.
31.9
KnowledgeFacts and expert knowledge.
32.0
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
29.0
MathMath problems.
33.1

Results

13 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
MATH level 5Math81.6%38.8Epoch AI
GPQA diamondKnowledge59.5%33.2Epoch AI
Artificial Analysis GPQA DiamondKnowledge57.8%27.8Artificial Analysis
Artificial Analysis MMMU-ProMultimodal53.0%31.9Artificial Analysis
Artificial Analysis IFBenchInstruction39.3%29.0Artificial Analysis
OTIS Mock AIME 2024-2025Math32.2%29.6Epoch AI
Artificial Analysis Long Context ReasoningReasoning31.3%29.9Artificial Analysis
τ²-Bench Tool-Agent-User EvaluationAgentic24.3%16.3Victor Barres et al.
Artificial Analysis Omniscience AccuracyKnowledge18.3%36.5Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge9.1%33.7Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge4.1%29.0Artificial Analysis
FrontierMath-2025-02-28-PrivateMath0.3%31.0Epoch AI
Critical Physics TasksReasoning0.0%38.4Artificial Analysis

13 benchmarks count, from 13 of 13 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedEpoch AI, collected directlyCC BY — free to use and redistribute with attribution

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Mistral

Mistral Medium 3.5 128B49.8Mistral Medium 3.543.0Mistral Small 438.4Mistral Small 4 (Reasoning)38.5Magistral Medium38.3