Noometry

Model comparison

Claude Opus 4.6 vs Mistral Large

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 31.9 on the Noometry Index. Mistral Large costs 3.3× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 28 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Mistral Large Mistral AI

31.9

Rank #263 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.6 leads 63.0 to 18.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for Claude Opus 4.6 and 8.5% for Mistral Large.
  • Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 131K.
  • Mistral Large has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.6Mistral Large
ProviderAnthropicMistral AI
Noometry Index58.231.9
Released2026-02-042024-02-26
WeightsProprietaryOpen
Context window1M131K
Max output128K16K
Input $ / M tokens$5$2
Output $ / M tokens$25$6
Results tracked6851

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.6: 57.2 (#20), Mistral Large: 34.3 (#240)

BenchmarkClaude Opus 4.6Mistral Large
LMArena Coding15361277
ALE-Bench996.5264.7
SWE-bench Verified78.7%—
FrontierCode26.6%—
SWE-bench Verified (bash only)75.6%—
LMArena WebDev1547—
SWE-bench Multilingual72%—
SciCode—36.2%
GSO41.2%—
WeirdML78%—
BigCodeBench Instruct—30%
LiveBench Coding—47.1%
BigCodeBench Complete—38.3%
AlgoTune1.47—
HumanEval+—62.2%
MBPP+—59.5%

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), Mistral Large: 28.6 (#89)

BenchmarkClaude Opus 4.6Mistral Large
Terminal-Bench79.8%—
APEX-Agents46.3%—
Berkeley Function Calling Leaderboard—38.4%
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
GBAEval44.1%—
LMArena Search1253—
METR Time Horizons78.9%—
Vending-Bench 28,018—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), Mistral Large: 15.8 (#310)

BenchmarkClaude Opus 4.6Mistral Large
SimpleBench67.6%22.5%
LMArena Hard Prompts15271257
DTBench91.2%65.1%
LMCA55.8%16.7%
Epoch Capabilities Index155.24128.52
ForecastBench6057.1
ARC-AGI-269.2%—
Kagi LLM Benchmark83.6%—
NYT Connections (extended)92.1%—
ARC-AGI-194%—
CritPt—0%
Chess Puzzles17%—
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—
LiveBench Reasoning—43.5%
Mystery Game Puzzles25%—
LiveBench Data Analysis—50.1%
LiveBench—48.4%

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), Mistral Large: 18.2 (#291)

BenchmarkClaude Opus 4.6Mistral Large
OTIS Mock AIME 2024-202594.4%8.5%
LMArena Math15191262
FrontierMath (Feb 2025 set)40.7%0.3%
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—
ProofBench50%—
Omni-MATH—28.1%
LiveBench Math—42.5%
MATH Level 5—50.3%
FrontierMath Tier 4 (v1)22.9%—

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), Mistral Large: 30.1 (#230)

BenchmarkClaude Opus 4.6Mistral Large
GPQA Diamond90.5%51.3%
Vectara Hallucination Rate12.2%4.5%
LMArena Expert15461232
Humanity's Last Exam34.4%—
SimpleQA Verified47%—
MMLU-Pro—59.9%
Confabulations—21.4%
GPQA (HELM)—43.5%
MMLU—80%

Multimodal Not comparable

Claude Opus 4.6: 37.3 (#74), Mistral Large: —

BenchmarkClaude Opus 4.6Mistral Large
LMArena Vision1316—
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), Mistral Large: 40.0 (#219)

BenchmarkClaude Opus 4.6Mistral Large
LMArena Non-English14891237
LMArena Chinese15511240
LMArena French15131325
LMArena German15021254
LMArena Japanese14841188
LMArena Korean14641202
LMArena Russian14971257
LMArena Spanish15101268

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), Mistral Large: 67.9 (#191)

BenchmarkClaude Opus 4.6Mistral Large
LMArena Instruction Following15231249
LiveBench Instruction Following—67.9%
IFEval—87.7%

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Mistral Large: 38.3 (#199)

BenchmarkClaude Opus 4.6Mistral Large
LMArena Longer Query15201261
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), Mistral Large: 40.7 (#242)

BenchmarkClaude Opus 4.6Mistral Large
LMArena Text15031266
LMArena Creative Writing15051243
EQ-Bench Creative Writing1809985
LMArena Multi-Turn15131260
Short-Story Creative Writing—69%
WildBench—80.1%
EQ-Bench 41223—
LiveBench Language—39.4%

Frequently asked questions

Is Claude Opus 4.6 better than Mistral Large?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 31.9 on the Noometry Index. Mistral Large costs 3.3× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.6 or Mistral Large?

Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or Mistral Large better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 34.3 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 131K.

How many benchmarks do Claude Opus 4.6 and Mistral Large share?

28 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Mistral Large has 51.

Related comparisons

Go deeper