Model comparison
Grok 3 vs Ministral 8B
Grok 3 is the stronger model overall, scoring 39.9 to 28.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. Grok 3 scores higher in 8 categories and Ministral 8B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 12.6.
- The biggest single-benchmark swing is MATH Level 5: 88.7% for Grok 3 and 14.9% for Ministral 8B.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Ministral 8B | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 39.9 | 28.2 |
| Released | 2025-04-09 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 40 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), Ministral 8B: 35.0 (#230)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1432 | 1202 |
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.5 (#76), Ministral 8B: 16.4 (#148)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
| BALROG | 29.5% | — |
Reasoning Ministral 8B leads
Grok 3: 13.7 (#333), Ministral 8B: 18.4 (#281)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1191 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| DTBench | — | 45.7% |
| Epoch Capabilities Index | 138.33 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Ministral 8B: 25.7 (#267)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| LMArena Math | 1391 | 1188 |
| MATH Level 5 | 88.7% | 14.9% |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), Ministral 8B: 12.6 (#297)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| GPQA Diamond | 75.8% | 27.1% |
| Vectara Hallucination Rate | 5.8% | 7.4% |
| LMArena Expert | 1421 | 1170 |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Ministral 8B: 35.1 (#247)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1410 | 1165 |
| LMArena Chinese | 1448 | 1193 |
| LMArena Russian | 1416 | 1195 |
| LMArena French | 1460 | — |
| LMArena German | 1431 | — |
| LMArena Japanese | 1387 | — |
| LMArena Korean | 1373 | — |
| LMArena Spanish | 1417 | — |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Ministral 8B: 60.5 (#250)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1409 | 1161 |
| IFEval | 88.4% | — |
Long Context Grok 3 leads
Grok 3: 38.7 (#192), Ministral 8B: 36.7 (#227)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1439 | 1212 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Ministral 8B: 39.6 (#246)
| Benchmark | Grok 3 | Ministral 8B |
|---|---|---|
| LMArena Text | 1426 | 1191 |
| LMArena Creative Writing | 1414 | 1175 |
| LMArena Multi-Turn | 1425 | 1166 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Ministral 8B?
Grok 3 is the stronger model overall, scoring 39.9 to 28.2 on the Noometry Index.
Is Grok 3 or Ministral 8B better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 35.0 in the Noometry coding category.
How many benchmarks do Grok 3 and Ministral 8B share?
15 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Ministral 8B has 17.