Magistral Medium

Magistral Medium is a model from Mistral. 10 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.38.3 ±6.1
CoverageShare of the index weight with results.90%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.N/A
EloLMArena rating and rank.1255 (#280)

The index is a score out of 100. The ± range shows how much it can change.

11,468 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
34.1
CodingCode writing and repair.
46.3
ReasoningLogic problems and puzzles.
34.9
MultimodalTasks with images and text.
32.4
KnowledgeFacts and expert knowledge.
32.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
52.7

Results

10 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
AIMEMath83.5%52.716 Apr 2026Vals AI
AIMEMath83.5%52.716 Apr 2026Vals AI
LiveCodeBenchCoding74.9%52.41 Sept 2026Vals AI
LiveCodeBenchCoding74.9%52.41 Sept 2026Vals AI
MGSMMultilingual74.6%9 Jan 2026Vals AI
MGSMMultilingual74.6%9 Jan 2026Vals AI
MMLU ProKnowledge68.7%28.61 Sept 2026Vals AI
MMLU ProKnowledge68.7%28.61 Sept 2026Vals AI
MMMU ProMultimodal64.6%32.41 Sept 2026Vals AI
MMMU ProMultimodal64.6%32.41 Sept 2026Vals AI
GPQA DiamondKnowledge62.4%35.81 Sept 2026Vals AI
GPQA DiamondKnowledge62.4%35.81 Sept 2026Vals AI
Terminal-Bench 1.0Agentic28.8%35.912 Jan 2026Vals AI
Terminal-Bench 1.0Agentic28.8%35.912 Jan 2026Vals AI
Terminal-Bench 2.0Agentic13.5%32.34 Jun 2026Vals AI
Terminal-Bench 2.0Agentic13.5%32.34 Jun 2026Vals AI
ARC-AGI-1 (semi-private)Reasoning5.9%30.0ARC Prize Foundation
IOI v1Coding0.7%40.39 Aug 2026Vals AI
IOI v1Coding0.7%40.39 Aug 2026Vals AI
ARC-AGI-2 (semi-private)Reasoning0.0%39.7ARC Prize Foundation

10 benchmarks count, from 18 of 20 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 authorsVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AIARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial use

More from Mistral

Mistral Medium 3.5 128B49.8Mistral Medium 3.543.0Mistral Small 438.4Mistral Small 4 (Reasoning)38.5Magistral Small35.7