Mistral Large

Mistral Large is a model from Mistral. 12 benchmarks count toward its score, in 5 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.28.7 ±7.2
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.67/s
Input / 1MUS dollars per 1M input tokens.$2
Output / 1MUS dollars per 1M output tokens.$6
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.1176 (#316)

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

62,436 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.
29.3
CodingCode writing and repair.
33.1
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
35.1
KnowledgeFacts and expert knowledge.
32.7
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
18.6

Results

12 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.
MGSMMultilingual87.2%9 Jan 2026Vals AI
MGSMMultilingual86.3%9 Jan 2026Vals AI
MGSMMultilingual85.4%9 Jan 2026Vals AI
MMLU ProKnowledge79.8%46.31 Sept 2026Vals AI
MMLU ProKnowledge74.8%38.31 Sept 2026Vals AI
MATH 500Math74.4%25.09 Jan 2026Vals AI
MATH 500Math74.4%25.09 Jan 2026Vals AI
MMLU ProKnowledge69.7%30.31 Sept 2026Vals AI
GPQA DiamondKnowledge68.4%41.41 Sept 2026Vals AI
MMMU ProMultimodal66.2%35.11 Sept 2026Vals AI
MMMU ProMultimodal66.2%35.11 Sept 2026Vals AI
GPQA DiamondKnowledge58.1%31.91 Sept 2026Vals AI
LiveCodeBenchCoding55.3%34.61 Sept 2026Vals AI
GPQA DiamondKnowledge47.7%22.31 Sept 2026Vals AI
LiveCodeBenchCoding46.2%26.41 Sept 2026Vals AI
AIMEMath42.9%33.716 Apr 2026Vals AI
SWE-benchCoding41.4%30.71 Sept 2026Vals AI
SWE-benchCoding41.4%30.71 Sept 2026Vals AI
GPQA diamondKnowledge38.8%14.0Epoch AI
LiveCodeBenchCoding37.1%18.11 Sept 2026Vals AI
AIMEMath26.0%25.916 Apr 2026Vals AI
MATH level 5Math24.5%10.7Epoch AI
Terminal-Bench 1.0Agentic21.3%29.612 Jan 2026Vals AI
Terminal-Bench 1.0Agentic21.3%29.612 Jan 2026Vals AI
AIMEMath9.2%18.016 Apr 2026Vals AI
Terminal-Bench 2.0Agentic9.0%29.14 Jun 2026Vals AI
Terminal-Bench 2.0Agentic9.0%29.14 Jun 2026Vals AI
IOI v1Coding4.0%42.29 Aug 2026Vals AI
IOI v1Coding4.0%42.29 Aug 2026Vals AI
OTIS Mock AIME 2024-2025Math1.9%12.7Epoch AI

12 benchmarks count, from 27 of 30 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 AIEpoch 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