Inference360
Mistral

Mistral Medium 3.5

Mistral Medium 3.5 is a model from Mistral. 9 benchmarks count toward its score, in 4 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.43.0 ±8.9
CoverageShare of the index weight with results.65%
SpeedOutput tokens per second.48/s
Input / 1MUS dollars per 1M input tokens.$1.5 batch $0.75
Output / 1MUS dollars per 1M output tokens.$7.5 batch $3.75 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.1421 (#104)

50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.

10,996 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
47.2
CodingCode writing and repair.
47.5
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
24.8
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
53.1

Results

9 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.
MMLU ProKnowledge75.3%39.2—1 Sept 2026Vals AI
SWE-benchCoding66.4%50.8—1 Sept 2026Vals AI
Terminal-Bench 2.1Agentic39.0%47.0—21 Sept 2026Vals AI
GPQA DiamondKnowledge34.8%10.4—1 Sept 2026Vals AI
Terminal-Bench 2.0Agentic30.3%44.3—4 Jun 2026Vals AI
ProofBench v1.1Math9.0%53.1—21 Sept 2026Vals AI
Code MigrationCoding5.1%48.2—21 Sept 2026Vals AI
Vibe Code Bench v1.1Coding2.9%43.4OpenHands21 Sept 2026Vals AI
Agent Arena steerabilityAgentic-6.060.6—15 Sept 2026LMArena
Agent Arena task outcomeAgentic-15.150.4—15 Sept 2026LMArena
Agent Arena command recoveryAgentic-15.849.6—15 Sept 2026LMArena

9 benchmarks count, from 11 of 11 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 statedVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AILMArena, collected directlyCC BY 4.0 (lmarena-ai/leaderboard-dataset on Hugging Face)

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 Small 438.4Mistral Small 4 (Reasoning)38.5Magistral Medium38.3Magistral Small35.7