Model comparison
Codestral vs Grok 4
Grok 4 is the stronger model overall, scoring 47.8 to 30.1 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Codestral scores higher in 0 categories and Grok 4 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Grok 4 leads 49.9 to 26.9.
- The biggest single-benchmark swing is Aider Polyglot: 11.1% for Codestral and 79.6% for Grok 4.
- Codestral has downloadable open weights; the other is API-only.
Side by side
| Codestral | Grok 4 | |
|---|---|---|
| Provider | Mistral AI | xAI |
| Noometry Index | 30.1 | 47.8 |
| Released | 2024-05-29 | 2025-07-09 |
| Weights | Open | Proprietary |
| Context window | 256K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Codestral: 26.9 (#316), Grok 4: 49.9 (#44)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| Aider Polyglot | 11.1% | 79.6% |
| WeirdML | — | 45.7% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1408 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Grok 4: 32.1 (#62)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Grok 4 leads
Codestral: 19.1 (#244), Grok 4: 36.9 (#59)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 73.6% |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| LMArena Hard Prompts | — | 1409 |
| Epoch Capabilities Index | — | 146.46 |
| ForecastBench | — | 60.9 |
Math Not comparable
Codestral: —, Grok 4: 46.5 (#58)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 84% |
| Omni-MATH | — | 60.3% |
| LMArena Math | — | 1422 |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Not comparable
Codestral: —, Grok 4: 53.7 (#50)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| GPQA Diamond | — | 87% |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
| LMArena Expert | — | 1417 |
Multimodal Not comparable
Codestral: —, Grok 4: 33.1 (#89)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1211 |
| GeoBench | — | 45% |
Multilingual Not comparable
Codestral: —, Grok 4: 52.0 (#98)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| LMArena Non-English | — | 1403 |
| LMArena Chinese | — | 1428 |
| LMArena French | — | 1418 |
| LMArena German | — | 1429 |
| LMArena Japanese | — | 1396 |
| LMArena Korean | — | 1376 |
| LMArena Russian | — | 1409 |
| LMArena Spanish | — | 1419 |
Instruction Following Not comparable
Codestral: —, Grok 4: 79.4 (#4)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| IFEval | — | 94.9% |
| LMArena Instruction Following | — | 1387 |
Long Context Not comparable
Codestral: —, Grok 4: 63.1 (#4)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| Fiction.LiveBench | — | 94.4% |
| LMArena Longer Query | — | 1409 |
Writing & Preference Not comparable
Codestral: —, Grok 4: 58.7 (#111)
| Benchmark | Codestral | Grok 4 |
|---|---|---|
| LMArena Text | — | 1412 |
| LMArena Creative Writing | — | 1397 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |
| LMArena Multi-Turn | — | 1416 |
Frequently asked questions
Is Codestral better than Grok 4?
Grok 4 is the stronger model overall, scoring 47.8 to 30.1 on the Noometry Index.
Is Codestral or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 49.9 versus 26.9 in the Noometry coding category.
How many benchmarks do Codestral and Grok 4 share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Grok 4 has 48.