Model comparison
Grok 3 vs Mistral Medium
Grok 3 is the stronger model overall, scoring 39.9 to 36.3 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AISummary
- They share 25 benchmarks with published results for both. Grok 3 scores higher in 6 categories and Mistral Medium in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 32.2% for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Mistral Medium | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 39.9 | 36.3 |
| Released | 2025-04-09 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 40 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| WeirdML | 37.2% | 43.7% |
| LMArena Coding | 1432 | 1434 |
| FrontierCode | — | 8% |
| Aider Polyglot | 53.3% | — |
| SciCode | — | 40.2% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.5 (#76), Mistral Medium: 28.3 (#90)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| BALROG | 29.5% | — |
Reasoning Mistral Medium leads
Grok 3: 13.7 (#333), Mistral Medium: 24.0 (#167)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 61.3% | 50% |
| LMArena Hard Prompts | 1434 | 1426 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 138.33 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Mistral Medium: 28.1 (#245)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 32.2% |
| LMArena Math | 1391 | 1408 |
| MATH Level 5 | 88.7% | 81.6% |
| FrontierMath (Feb 2025 set) | 3.8% | 0.3% |
| ProofBench | — | 9% |
| Omni-MATH | 46.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), Mistral Medium: 25.0 (#265)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 75.8% | 59.5% |
| Vectara Hallucination Rate | 5.8% | 22.7% |
| LMArena Expert | 1421 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Grok 3: —, Mistral Medium: 35.3 (#88)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Too close to call
Grok 3: 52.3 (#87), Mistral Medium: 52.1 (#91)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1410 | 1408 |
| LMArena Chinese | 1448 | 1447 |
| LMArena French | 1460 | 1459 |
| LMArena German | 1431 | 1432 |
| LMArena Japanese | 1387 | 1378 |
| LMArena Korean | 1373 | 1380 |
| LMArena Russian | 1416 | 1411 |
| LMArena Spanish | 1417 | 1433 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Mistral Medium: 73.7 (#116)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1409 | 1398 |
| IFEval | 88.4% | — |
Long Context Mistral Medium leads
Grok 3: 38.7 (#192), Mistral Medium: 42.9 (#114)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1439 | 1406 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Mistral Medium leads
Grok 3: 55.8 (#141), Mistral Medium: 60.0 (#103)
| Benchmark | Grok 3 | Mistral Medium |
|---|---|---|
| LMArena Text | 1426 | 1424 |
| LMArena Creative Writing | 1414 | 1391 |
| Short-Story Creative Writing | 76.4% | 77.3% |
| LMArena Multi-Turn | 1425 | 1418 |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Mistral Medium?
Grok 3 is the stronger model overall, scoring 39.9 to 36.3 on the Noometry Index.
Is Grok 3 or Mistral Medium better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 34.2 in the Noometry coding category.
How many benchmarks do Grok 3 and Mistral Medium share?
25 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Mistral Medium has 36.