Noometry

Model comparison

Grok 3 vs Mistral Large

Grok 3 is the stronger model overall, scoring 39.6 to 31.6 on the Noometry Index.

Last verified . 32 shared benchmarks.

Grok 3 xAI

39.6

Rank #150 Confirmed

Mistral Large Mistral AI

31.6

Rank #258 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Grok 3 scores higher in 8 categories and Mistral Large in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 3 leads 36.2 to 17.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 8.5% for Mistral Large.
  • Mistral Large has downloadable open weights; the other is API-only.

Side by side

Grok 3Mistral Large
ProviderxAIMistral AI
Noometry Index39.631.6
Released2025-04-092024-02-26
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked4051

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

Category by category

Coding Grok 3 leads

Grok 3: 41.5 (#113), Mistral Large: 33.8 (#240)

BenchmarkGrok 3Mistral Large
LMArena Coding14321277
Aider Polyglot53.3%—
SciCode—36.2%
WeirdML37.2%—
BigCodeBench Instruct—30%
LiveBench Coding—47.1%
BigCodeBench Complete—38.3%
ALE-Bench—264.7
HumanEval+—62.2%
MBPP+—59.5%

Agentic & Tool Use Grok 3 leads

Grok 3: 30.2 (#69), Mistral Large: 28.4 (#83)

BenchmarkGrok 3Mistral Large
Berkeley Function Calling Leaderboard—38.4%
BALROG29.5%—

Reasoning Mistral Large leads

Grok 3: 13.8 (#322), Mistral Large: 15.4 (#305)

BenchmarkGrok 3Mistral Large
SimpleBench36.1%22.5%
LMArena Hard Prompts14331257
Epoch Capabilities Index138.34128.52
ARC-AGI-20%—
Kagi LLM Benchmark61.3%—
ARC-AGI-15.5%—
CritPt—0%
LiveBench Reasoning—43.5%
DTBench—65.1%
LiveBench Data Analysis—50.1%
LMCA—16.7%
ForecastBench—57.1
LiveBench—48.4%

Math Grok 3 leads

Grok 3: 36.2 (#122), Mistral Large: 17.1 (#285)

BenchmarkGrok 3Mistral Large
OTIS Mock AIME 2024-202555.6%8.5%
Omni-MATH46.4%28.1%
LMArena Math13901262
MATH Level 588.7%50.3%
FrontierMath (Feb 2025 set)3.8%0.3%
LiveBench Math—42.5%
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 3 leads

Grok 3: 46.0 (#76), Mistral Large: 30.0 (#224)

BenchmarkGrok 3Mistral Large
GPQA Diamond75.8%51.3%
MMLU-Pro78.8%59.9%
Confabulations14.2%21.4%
Vectara Hallucination Rate5.8%4.5%
GPQA (HELM)65%43.5%
LMArena Expert14201232
MMLU—80%

Multilingual Grok 3 leads

Grok 3: 52.5 (#81), Mistral Large: 40.1 (#214)

BenchmarkGrok 3Mistral Large
LMArena Non-English14111237
LMArena Chinese14481240
LMArena French14601324
LMArena German14311254
LMArena Japanese13891187
LMArena Korean13741202
LMArena Russian14161257
LMArena Spanish14171268

Instruction Following Grok 3 leads

Grok 3: 75.2 (#69), Mistral Large: 68.1 (#186)

BenchmarkGrok 3Mistral Large
IFEval88.4%87.7%
LMArena Instruction Following14091249
LiveBench Instruction Following—67.9%

Long Context Too close to call

Grok 3: 38.7 (#187), Mistral Large: 38.3 (#194)

BenchmarkGrok 3Mistral Large
LMArena Longer Query14391262
Fiction.LiveBench58.3%—

Writing & Preference Grok 3 leads

Grok 3: 56.0 (#136), Mistral Large: 40.9 (#237)

BenchmarkGrok 3Mistral Large
LMArena Text14261266
LMArena Creative Writing14141243
Short-Story Creative Writing76.4%69%
EQ-Bench Creative Writing1186985
WildBench84.9%80.1%
LMArena Multi-Turn14241260
LiveBench Language—39.4%

Frequently asked questions

Is Grok 3 better than Mistral Large?

Grok 3 is the stronger model overall, scoring 39.6 to 31.6 on the Noometry Index.

Is Grok 3 or Mistral Large better for coding?

Grok 3 scores higher on coding benchmarks: 41.5 versus 33.8 in the Noometry coding category.

How many benchmarks do Grok 3 and Mistral Large share?

32 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Mistral Large has 51.

Related comparisons

Go deeper