Model comparison
Grok 3 vs Mistral Large
Grok 3 is the stronger model overall, scoring 39.9 to 31.9 on the Noometry Index.
Last verified . 32 shared benchmarks.
Mistral AISummary
- 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 38.0 to 18.2.
- 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 3 | Mistral Large | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 39.9 | 31.9 |
| Released | 2025-04-09 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 40 | 51 |
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 Large: 34.3 (#240)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| LMArena Coding | 1432 | 1277 |
| Aider Polyglot | 53.3% | — |
| SciCode | — | 36.2% |
| WeirdML | 37.2% | — |
| 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: 30.5 (#76), Mistral Large: 28.6 (#89)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| BALROG | 29.5% | — |
Reasoning Mistral Large leads
Grok 3: 13.7 (#333), Mistral Large: 15.8 (#310)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| SimpleBench | 36.1% | 22.5% |
| LMArena Hard Prompts | 1434 | 1257 |
| Epoch Capabilities Index | 138.33 | 128.52 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| 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: 38.0 (#145), Mistral Large: 18.2 (#291)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 8.5% |
| Omni-MATH | 46.4% | 28.1% |
| LMArena Math | 1391 | 1262 |
| MATH Level 5 | 88.7% | 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: 46.2 (#82), Mistral Large: 30.1 (#230)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| GPQA Diamond | 75.8% | 51.3% |
| MMLU-Pro | 78.8% | 59.9% |
| Confabulations | 14.2% | 21.4% |
| Vectara Hallucination Rate | 5.8% | 4.5% |
| GPQA (HELM) | 65% | 43.5% |
| LMArena Expert | 1421 | 1232 |
| MMLU | — | 80% |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Mistral Large: 40.0 (#219)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1410 | 1237 |
| LMArena Chinese | 1448 | 1240 |
| LMArena French | 1460 | 1325 |
| LMArena German | 1431 | 1254 |
| LMArena Japanese | 1387 | 1188 |
| LMArena Korean | 1373 | 1202 |
| LMArena Russian | 1416 | 1257 |
| LMArena Spanish | 1417 | 1268 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Mistral Large: 67.9 (#191)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| IFEval | 88.4% | 87.7% |
| LMArena Instruction Following | 1409 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Too close to call
Grok 3: 38.7 (#192), Mistral Large: 38.3 (#199)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1439 | 1261 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Mistral Large: 40.7 (#242)
| Benchmark | Grok 3 | Mistral Large |
|---|---|---|
| LMArena Text | 1426 | 1266 |
| LMArena Creative Writing | 1414 | 1243 |
| Short-Story Creative Writing | 76.4% | 69% |
| EQ-Bench Creative Writing | 1186 | 985 |
| WildBench | 84.9% | 80.1% |
| LMArena Multi-Turn | 1425 | 1260 |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Grok 3 better than Mistral Large?
Grok 3 is the stronger model overall, scoring 39.9 to 31.9 on the Noometry Index.
Is Grok 3 or Mistral Large better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 34.3 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.