Model comparison
Grok 3 vs Mixtral 8x22B
Grok 3 is the stronger model overall, scoring 39.6 to 26.7 on the Noometry Index.
Last verified . 26 shared benchmarks.
Mistral AISummary
- They share 26 benchmarks with published results for both. Grok 3 scores higher in 8 categories and Mixtral 8x22B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.0 to 15.1.
- The biggest single-benchmark swing is MATH Level 5: 88.7% for Grok 3 and 24.2% for Mixtral 8x22B.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Mixtral 8x22B | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 39.6 | 26.7 |
| Released | 2025-04-09 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | — | 64K |
| Max output | — | 64K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 40 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.5 (#113), Mixtral 8x22B: 23.8 (#324)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 37.2% | 3.2% |
| LMArena Coding | 1432 | 1166 |
| Aider Polyglot | 53.3% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.2 (#69), Mixtral 8x22B: 22.8 (#119)
Reasoning Mixtral 8x22B leads
Grok 3: 13.8 (#322), Mixtral 8x22B: 19.1 (#246)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1150 |
| Epoch Capabilities Index | 138.34 | 122 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |
Math Grok 3 leads
Grok 3: 36.2 (#122), Mixtral 8x22B: 21.2 (#271)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 46.4% | 16.3% |
| LMArena Math | 1390 | 1184 |
| MATH Level 5 | 88.7% | 24.2% |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), Mixtral 8x22B: 15.1 (#288)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 75.8% | 34.1% |
| MMLU-Pro | 78.8% | 46% |
| GPQA (HELM) | 65% | 33.4% |
| LMArena Expert | 1420 | 1113 |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| MMLU | — | 77.8% |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), Mixtral 8x22B: 32.9 (#250)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1411 | 1128 |
| LMArena Chinese | 1448 | 1116 |
| LMArena French | 1460 | 1165 |
| LMArena German | 1431 | 1141 |
| LMArena Japanese | 1389 | 1037 |
| LMArena Korean | 1374 | 1056 |
| LMArena Russian | 1416 | 1158 |
| LMArena Spanish | 1417 | 1150 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), Mixtral 8x22B: 57.9 (#261)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| IFEval | 88.4% | 72.4% |
| LMArena Instruction Following | 1409 | 1147 |
Long Context Grok 3 leads
Grok 3: 38.7 (#187), Mixtral 8x22B: 34.6 (#242)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1439 | 1144 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 56.0 (#136), Mixtral 8x22B: 37.1 (#257)
| Benchmark | Grok 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1426 | 1162 |
| LMArena Creative Writing | 1414 | 1141 |
| WildBench | 84.9% | 71.1% |
| LMArena Multi-Turn | 1424 | 1130 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
Frequently asked questions
Is Grok 3 better than Mixtral 8x22B?
Grok 3 is the stronger model overall, scoring 39.6 to 26.7 on the Noometry Index.
Is Grok 3 or Mixtral 8x22B better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 23.8 in the Noometry coding category.
How many benchmarks do Grok 3 and Mixtral 8x22B share?
26 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Mixtral 8x22B has 34.