Model comparison
Codestral vs Granite 4.0 Micro
Codestral is the stronger model overall, scoring 30.6 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 11× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 131K.
- Granite 4.0 Micro has downloadable open weights; the other is API-only.
Side by side
| Codestral | Granite 4.0 Micro | |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.6 | 29.0 |
| Released | 2024-05-29 | 2025-10-02 |
| Weights | Proprietary | Open |
| Context window | 256K | 131K |
| Max output | 8K | 118K |
| Input $ / M tokens | $0.30 | $0.017 |
| Output $ / M tokens | $0.90 | $0.11 |
| Results tracked | 7 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codestral: 27.3 (#321), Granite 4.0 Micro: —
| Benchmark | Codestral | Granite 4.0 Micro |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Too close to call
Codestral: 19.8 (#251), Granite 4.0 Micro: 19.2 (#265)
| Benchmark | Codestral | Granite 4.0 Micro |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| Chess Puzzles | — | 0% |
Math Not comparable
Codestral: —, Granite 4.0 Micro: 12.0 (#307)
| Benchmark | Codestral | Granite 4.0 Micro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.8% |
| Omni-MATH | — | 20.9% |
Knowledge Not comparable
Codestral: —, Granite 4.0 Micro: 9.9 (#304)
| Benchmark | Codestral | Granite 4.0 Micro |
|---|---|---|
| GPQA Diamond | — | 28.3% |
| MMLU-Pro | — | 39.5% |
| GPQA (HELM) | — | 30.7% |
Instruction Following Not comparable
Codestral: —, Granite 4.0 Micro: 69.9 (#169)
| Benchmark | Codestral | Granite 4.0 Micro |
|---|---|---|
| IFEval | — | 84.9% |
Writing & Preference Not comparable
Codestral: —, Granite 4.0 Micro: 46.7 (#216)
| Benchmark | Codestral | Granite 4.0 Micro |
|---|---|---|
| WildBench | — | 67% |
Frequently asked questions
Is Codestral better than Granite 4.0 Micro?
Codestral is the stronger model overall, scoring 30.6 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 11× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.
Which is cheaper, Codestral or Granite 4.0 Micro?
Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; Codestral lists at $0.30 and $0.90.
Which has the bigger context window?
Codestral does, with 256K tokens against 131K.
How many benchmarks do Codestral and Granite 4.0 Micro share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Granite 4.0 Micro has 8.