Model comparison
Grok-2 (Dec 2024) vs Mistral Large
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 31.9 on the Noometry Index.
Last verified . 33 shared benchmarks.
Mistral AISummary
- They share 33 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 5 categories and Mistral Large in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok-2 (Dec 2024) leads 48.6 to 40.7.
- The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 50.3% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Grok-2 (Dec 2024) | Mistral Large | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 33.7 | 31.9 |
| Released | 2024-08-13 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 34 | 51 |
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 Large: 34.3 (#240)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| LiveBench Coding | 46.4% | 47.1% |
| LMArena Coding | 1287 | 1277 |
| SciCode | — | 36.2% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | — | 30% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
Grok-2 (Dec 2024): —, Mistral Large: 28.6 (#89)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 16.9 (#299), Mistral Large: 15.8 (#310)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| SimpleBench | 22.7% | 22.5% |
| LiveBench Reasoning | 54.8% | 43.5% |
| LMArena Hard Prompts | 1272 | 1257 |
| DTBench | 65.2% | 65.1% |
| LiveBench Data Analysis | 54.5% | 50.1% |
| Epoch Capabilities Index | 130.48 | 128.52 |
| LiveBench | 54.3% | 48.4% |
| CritPt | — | 0% |
| LMCA | — | 16.7% |
| ForecastBench | — | 57.1 |
Math Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 20.8 (#284), Mistral Large: 18.2 (#291)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 8.5% |
| LiveBench Math | 54.9% | 42.5% |
| LMArena Math | 1283 | 1262 |
| MATH Level 5 | 63.5% | 50.3% |
| FrontierMath (Feb 2025 set) | 0.7% | 0.3% |
| Omni-MATH | — | 28.1% |
Knowledge Too close to call
Grok-2 (Dec 2024): 29.8 (#233), Mistral Large: 30.1 (#230)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| GPQA Diamond | 53.8% | 51.3% |
| Confabulations | 20.1% | 21.4% |
| LMArena Expert | 1254 | 1232 |
| MMLU-Pro | — | 59.9% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 43.1 (#188), Mistral Large: 40.0 (#219)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| LMArena Non-English | 1282 | 1237 |
| LMArena Chinese | 1289 | 1240 |
| LMArena French | 1318 | 1325 |
| LMArena German | 1287 | 1254 |
| LMArena Japanese | 1244 | 1188 |
| LMArena Korean | 1237 | 1202 |
| LMArena Russian | 1286 | 1257 |
| LMArena Spanish | 1281 | 1268 |
Instruction Following Mistral Large leads
Grok-2 (Dec 2024): 66.9 (#202), Mistral Large: 67.9 (#191)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 69.6% | 67.9% |
| LMArena Instruction Following | 1270 | 1249 |
| IFEval | — | 87.7% |
Long Context Too close to call
Grok-2 (Dec 2024): 38.8 (#190), Mistral Large: 38.3 (#199)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1276 | 1261 |
Writing & Preference Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 48.6 (#198), Mistral Large: 40.7 (#242)
| Benchmark | Grok-2 (Dec 2024) | Mistral Large |
|---|---|---|
| LMArena Text | 1305 | 1266 |
| LMArena Creative Writing | 1284 | 1243 |
| Short-Story Creative Writing | 63.6% | 69% |
| LMArena Multi-Turn | 1290 | 1260 |
| LiveBench Language | 45.6% | 39.4% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Mistral Large?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 31.9 on the Noometry Index.
Is Grok-2 (Dec 2024) or Mistral Large better for coding?
They score almost the same on coding (33.3 vs 34.3); test both on your own repository before choosing.
How many benchmarks do Grok-2 (Dec 2024) and Mistral Large share?
33 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Mistral Large has 51.