Model comparison
Grok 3 vs Mistral Small
Grok 3 is the stronger model overall, scoring 39.6 to 33.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Grok 3 scores higher in 7 categories and Mistral Small in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 3 leads 36.2 to 15.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 5.8% for Mistral Small.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Mistral Small | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 39.6 | 33.1 |
| Released | 2025-04-09 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 40 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.5 (#113), Mistral Small: 33.5 (#242)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| LMArena Coding | 1432 | 1363 |
| Aider Polyglot | 53.3% | — |
| SciCode | — | 26.5% |
| WeirdML | 37.2% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.2 (#69), Mistral Small: 27.9 (#87)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| BALROG | 29.5% | — |
Reasoning Mistral Small leads
Grok 3: 13.8 (#322), Mistral Small: 19.3 (#238)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 61.3% | 37.8% |
| LMArena Hard Prompts | 1433 | 1336 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 138.34 | — |
| LiveBench | — | 44% |
Math Grok 3 leads
Grok 3: 36.2 (#122), Mistral Small: 15.4 (#287)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 5.8% |
| LMArena Math | 1390 | 1341 |
| MATH Level 5 | 88.7% | 46.8% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | — | 39.9% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), Mistral Small: 30.9 (#214)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| GPQA Diamond | 75.8% | 47.5% |
| Vectara Hallucination Rate | 5.8% | 5.1% |
| LMArena Expert | 1420 | 1293 |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| GPQA (HELM) | 65% | — |
| MMLU | — | 68.7% |
Multimodal Not comparable
Grok 3: —, Mistral Small: 32.9 (#91)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), Mistral Small: 45.7 (#164)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1411 | 1315 |
| LMArena Chinese | 1448 | 1342 |
| LMArena French | 1460 | 1337 |
| LMArena German | 1431 | 1341 |
| LMArena Japanese | 1389 | 1275 |
| LMArena Korean | 1374 | 1260 |
| LMArena Russian | 1416 | 1324 |
| LMArena Spanish | 1417 | 1346 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), Mistral Small: 66.6 (#204)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1409 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 88.4% | — |
Long Context Mistral Small leads
Grok 3: 38.7 (#187), Mistral Small: 40.4 (#151)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1439 | 1327 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 56.0 (#136), Mistral Small: 52.6 (#165)
| Benchmark | Grok 3 | Mistral Small |
|---|---|---|
| LMArena Text | 1426 | 1338 |
| LMArena Creative Writing | 1414 | 1304 |
| LMArena Multi-Turn | 1424 | 1344 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Grok 3 better than Mistral Small?
Grok 3 is the stronger model overall, scoring 39.6 to 33.1 on the Noometry Index.
Is Grok 3 or Mistral Small better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 33.5 in the Noometry coding category.
How many benchmarks do Grok 3 and Mistral Small share?
22 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Mistral Small has 39.