Model comparison
Grok-2 (Dec 2024) vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 33.7 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 1 category and Mistral Medium in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 48.6.
- The biggest single-benchmark swing is WeirdML: 22.2% for Grok-2 (Dec 2024) and 43.7% for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Grok-2 (Dec 2024) | Mistral Medium | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 33.7 | 36.3 |
| Released | 2024-08-13 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 34 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok-2 (Dec 2024): 33.3 (#258), Mistral Medium: 34.2 (#243)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| WeirdML | 22.2% | 43.7% |
| LMArena Coding | 1287 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| LiveBench Coding | 46.4% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Grok-2 (Dec 2024): —, Mistral Medium: 28.3 (#90)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Grok-2 (Dec 2024): 16.9 (#299), Mistral Medium: 24.0 (#167)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1426 |
| DTBench | 65.2% | 75.5% |
| SimpleBench | 22.7% | — |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LiveBench Reasoning | 54.8% | — |
| LiveBench Data Analysis | 54.5% | — |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 130.48 | — |
| LiveBench | 54.3% | — |
Math Mistral Medium leads
Grok-2 (Dec 2024): 20.8 (#284), Mistral Medium: 28.1 (#245)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 32.2% |
| LMArena Math | 1283 | 1408 |
| MATH Level 5 | 63.5% | 81.6% |
| FrontierMath (Feb 2025 set) | 0.7% | 0.3% |
| ProofBench | — | 9% |
| LiveBench Math | 54.9% | — |
Knowledge Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 29.8 (#233), Mistral Medium: 25.0 (#265)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| GPQA Diamond | 53.8% | 59.5% |
| LMArena Expert | 1254 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Confabulations | 20.1% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
Grok-2 (Dec 2024): —, Mistral Medium: 35.3 (#88)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Grok-2 (Dec 2024): 43.1 (#188), Mistral Medium: 52.1 (#91)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1282 | 1408 |
| LMArena Chinese | 1289 | 1447 |
| LMArena French | 1318 | 1459 |
| LMArena German | 1287 | 1432 |
| LMArena Japanese | 1244 | 1378 |
| LMArena Korean | 1237 | 1380 |
| LMArena Russian | 1286 | 1411 |
| LMArena Spanish | 1281 | 1433 |
Instruction Following Mistral Medium leads
Grok-2 (Dec 2024): 66.9 (#202), Mistral Medium: 73.7 (#116)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1270 | 1398 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Mistral Medium leads
Grok-2 (Dec 2024): 38.8 (#190), Mistral Medium: 42.9 (#114)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1276 | 1406 |
Writing & Preference Mistral Medium leads
Grok-2 (Dec 2024): 48.6 (#198), Mistral Medium: 60.0 (#103)
| Benchmark | Grok-2 (Dec 2024) | Mistral Medium |
|---|---|---|
| LMArena Text | 1305 | 1424 |
| LMArena Creative Writing | 1284 | 1391 |
| Short-Story Creative Writing | 63.6% | 77.3% |
| LMArena Multi-Turn | 1290 | 1418 |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Mistral Medium better for coding?
They score almost the same on coding (33.3 vs 34.2); test both on your own repository before choosing.
How many benchmarks do Grok-2 (Dec 2024) and Mistral Medium share?
24 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Mistral Medium has 36.