Model comparison
Grok 3 vs Mistral
Grok 3 is the stronger model overall, scoring 39.9 to 29.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Grok 3 scores higher in 7 categories and Mistral in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 16.6.
- The biggest single-benchmark swing is MMLU-Pro: 78.8% for Grok 3 and 27.7% for Mistral.
Side by side
| Grok 3 | Mistral | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 39.9 | 29.9 |
| Released | 2025-04-09 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), Mistral: 33.8 (#250)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| LMArena Coding | 1432 | 1162 |
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
Agentic & Tool Use Not comparable
Grok 3: 30.5 (#76), Mistral: —
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Mistral leads
Grok 3: 13.7 (#333), Mistral: 22.2 (#200)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1149 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.33 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Mistral: 22.3 (#278)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| Omni-MATH | 46.4% | 7.2% |
| LMArena Math | 1391 | 1180 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), Mistral: 16.6 (#288)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| MMLU-Pro | 78.8% | 27.7% |
| GPQA (HELM) | 65% | 30.3% |
| LMArena Expert | 1421 | 1125 |
| GPQA Diamond | 75.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Mistral: 32.8 (#254)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| LMArena Non-English | 1410 | 1129 |
| LMArena Chinese | 1448 | 1109 |
| LMArena French | 1460 | 1180 |
| LMArena German | 1431 | 1155 |
| LMArena Japanese | 1387 | 1013 |
| LMArena Korean | 1373 | 1032 |
| LMArena Russian | 1416 | 1168 |
| LMArena Spanish | 1417 | 1143 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Mistral: 52.6 (#288)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| IFEval | 88.4% | 56.8% |
| LMArena Instruction Following | 1409 | 1152 |
Long Context Grok 3 leads
Grok 3: 38.7 (#192), Mistral: 35.0 (#245)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| LMArena Longer Query | 1439 | 1153 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Mistral: 37.0 (#260)
| Benchmark | Grok 3 | Mistral |
|---|---|---|
| LMArena Text | 1426 | 1165 |
| LMArena Creative Writing | 1414 | 1158 |
| WildBench | 84.9% | 66% |
| LMArena Multi-Turn | 1425 | 1147 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
Frequently asked questions
Is Grok 3 better than Mistral?
Grok 3 is the stronger model overall, scoring 39.9 to 29.9 on the Noometry Index.
Is Grok 3 or Mistral better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 33.8 in the Noometry coding category.
How many benchmarks do Grok 3 and Mistral share?
22 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Mistral has 22.