Model comparison
Grok 4 vs Mistral Medium
Grok 4 is the stronger model overall, scoring 47.8 to 36.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AISummary
- They share 25 benchmarks with published results for both. Grok 4 scores higher in 7 categories and Mistral Medium in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4 leads 53.7 to 24.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84% for Grok 4 and 32.2% for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Grok 4 | Mistral Medium | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 47.8 | 36.0 |
| Released | 2025-07-09 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 48 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Grok 4: 49.9 (#44), Mistral Medium: 33.8 (#241)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| WeirdML | 45.7% | 43.7% |
| LMArena Coding | 1408 | 1434 |
| FrontierCode | — | 8% |
| Aider Polyglot | 79.6% | — |
| SciCode | — | 40.2% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Grok 4 leads
Grok 4: 32.1 (#62), Mistral Medium: 28.1 (#84)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | 37.7% |
| Terminal-Bench | 27.2% | — |
| GDPval | 21.1% | — |
| Cybench | 43% | — |
| DeepResearch Bench | 47.3% | — |
| BALROG | 43.6% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 66.6% | — |
Reasoning Grok 4 leads
Grok 4: 36.9 (#59), Mistral Medium: 23.3 (#165)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 73.6% | 50% |
| LMArena Hard Prompts | 1409 | 1426 |
| ARC-AGI-2 | 16% | — |
| SimpleBench | 60.5% | — |
| ARC-AGI-1 | 66.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | 28% | — |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 146.46 | — |
| ForecastBench | 60.9 | — |
Math Grok 4 leads
Grok 4: 46.5 (#58), Mistral Medium: 27.2 (#238)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84% | 32.2% |
| LMArena Math | 1422 | 1409 |
| FrontierMath (Feb 2025 set) | 19.7% | 0.3% |
| ProofBench | — | 9% |
| Omni-MATH | 60.3% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Grok 4 leads
Grok 4: 53.7 (#50), Mistral Medium: 24.9 (#260)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 87% | 59.5% |
| LMArena Expert | 1417 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| MMLU-Pro | 85.1% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 22.7% |
| GPQA (HELM) | 72.7% | — |
Multimodal Mistral Medium leads
Grok 4: 33.1 (#89), Mistral Medium: 34.6 (#82)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1211 | 1172 |
| GeoBench | 45% | — |
Multilingual Too close to call
Grok 4: 52.0 (#98), Mistral Medium: 52.3 (#86)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1403 | 1408 |
| LMArena Chinese | 1428 | 1448 |
| LMArena French | 1418 | 1460 |
| LMArena German | 1429 | 1433 |
| LMArena Japanese | 1396 | 1378 |
| LMArena Korean | 1376 | 1382 |
| LMArena Russian | 1409 | 1411 |
| LMArena Spanish | 1419 | 1433 |
Instruction Following Grok 4 leads
Grok 4: 79.4 (#4), Mistral Medium: 73.9 (#111)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1387 | 1398 |
| IFEval | 94.9% | — |
Long Context Grok 4 leads
Grok 4: 63.1 (#4), Mistral Medium: 42.9 (#108)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1409 | 1406 |
| Fiction.LiveBench | 94.4% | — |
Writing & Preference Mistral Medium leads
Grok 4: 58.7 (#111), Mistral Medium: 60.2 (#97)
| Benchmark | Grok 4 | Mistral Medium |
|---|---|---|
| LMArena Text | 1412 | 1424 |
| LMArena Creative Writing | 1397 | 1391 |
| Short-Story Creative Writing | 76.9% | 77.3% |
| LMArena Multi-Turn | 1416 | 1418 |
| WildBench | 79.7% | — |
Frequently asked questions
Is Grok 4 better than Mistral Medium?
Grok 4 is the stronger model overall, scoring 47.8 to 36.0 on the Noometry Index.
Is Grok 4 or Mistral Medium better for coding?
Grok 4 scores higher on coding benchmarks: 49.9 versus 33.8 in the Noometry coding category.
How many benchmarks do Grok 4 and Mistral Medium share?
25 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Mistral Medium has 36.