Model comparison
Grok 3 vs Magistral Medium
Grok 3 is the stronger model overall, scoring 39.9 to 35.2 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Grok 3 scores higher in 7 categories and Magistral Medium in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Grok 3 leads 52.3 to 39.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 61.3% for Grok 3 and 16.2% for Magistral Medium.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Magistral Medium | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 39.9 | 35.2 |
| Released | 2025-04-09 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $5 |
| 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), Magistral Medium: 39.1 (#161)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| LMArena Coding | 1432 | 1319 |
| Aider Polyglot | 53.3% | — |
| SciCode | — | 39.2% |
| WeirdML | 37.2% | — |
Agentic & Tool Use Not comparable
Grok 3: 30.5 (#76), Magistral Medium: —
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Grok 3 leads
Grok 3: 13.7 (#333), Magistral Medium: 8.6 (#348)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 0% | 0% |
| Kagi LLM Benchmark | 61.3% | 16.2% |
| ARC-AGI-1 | 5.5% | 6.1% |
| LMArena Hard Prompts | 1434 | 1267 |
| SimpleBench | 36.1% | — |
| CritPt | — | 0.3% |
| Epoch Capabilities Index | 138.33 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Magistral Medium: 35.1 (#189)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| LMArena Math | 1391 | 1250 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| 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), Magistral Medium: 33.5 (#202)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1421 | 1223 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Magistral Medium: 39.6 (#224)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1410 | 1232 |
| LMArena Chinese | 1448 | 1227 |
| LMArena French | 1460 | 1267 |
| LMArena German | 1431 | 1248 |
| LMArena Japanese | 1387 | 1175 |
| LMArena Korean | 1373 | 1125 |
| LMArena Russian | 1416 | 1224 |
| LMArena Spanish | 1417 | 1271 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Magistral Medium: 66.0 (#211)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1409 | 1254 |
| IFEval | 88.4% | — |
Long Context Too close to call
Grok 3: 38.7 (#192), Magistral Medium: 39.3 (#183)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1439 | 1295 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Magistral Medium: 46.3 (#219)
| Benchmark | Grok 3 | Magistral Medium |
|---|---|---|
| LMArena Text | 1426 | 1255 |
| LMArena Creative Writing | 1414 | 1245 |
| LMArena Multi-Turn | 1425 | 1275 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Magistral Medium?
Grok 3 is the stronger model overall, scoring 39.9 to 35.2 on the Noometry Index.
Is Grok 3 or Magistral Medium better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 39.1 in the Noometry coding category.
How many benchmarks do Grok 3 and Magistral Medium share?
20 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Magistral Medium has 22.