Model comparison
Devstral Small 2505 vs Granite 4.0 Micro
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 3.7× less per token, which makes it the better buy when Devstral Small 2505'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 $0.10 / $0.30 for Devstral Small 2505.
- Granite 4.0 Micro accepts more context: 131K tokens versus 128K.
Side by side
| Devstral Small 2505 | Granite 4.0 Micro | |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 34.3 | 29.0 |
| Released | 2025-05-07 | 2025-10-02 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 128K | 118K |
| Input $ / M tokens | $0.10 | $0.017 |
| Output $ / M tokens | $0.30 | $0.11 |
| Results tracked | 4 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Devstral Small 2505: 38.9 (#166), Granite 4.0 Micro: —
| Benchmark | Devstral Small 2505 | Granite 4.0 Micro |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
Reasoning Too close to call
Devstral Small 2505: 19.7 (#252), Granite 4.0 Micro: 19.2 (#265)
| Benchmark | Devstral Small 2505 | Granite 4.0 Micro |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
Math Not comparable
Devstral Small 2505: —, Granite 4.0 Micro: 12.0 (#307)
| Benchmark | Devstral Small 2505 | Granite 4.0 Micro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.8% |
| Omni-MATH | — | 20.9% |
Knowledge Not comparable
Devstral Small 2505: —, Granite 4.0 Micro: 9.9 (#304)
| Benchmark | Devstral Small 2505 | Granite 4.0 Micro |
|---|---|---|
| GPQA Diamond | — | 28.3% |
| MMLU-Pro | — | 39.5% |
| GPQA (HELM) | — | 30.7% |
Instruction Following Not comparable
Devstral Small 2505: —, Granite 4.0 Micro: 69.9 (#169)
| Benchmark | Devstral Small 2505 | Granite 4.0 Micro |
|---|---|---|
| IFEval | — | 84.9% |
Writing & Preference Not comparable
Devstral Small 2505: —, Granite 4.0 Micro: 46.7 (#216)
| Benchmark | Devstral Small 2505 | Granite 4.0 Micro |
|---|---|---|
| WildBench | — | 67% |
Frequently asked questions
Is Devstral Small 2505 better than Granite 4.0 Micro?
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 3.7× less per token, which makes it the better buy when Devstral Small 2505's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 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; Devstral Small 2505 lists at $0.10 and $0.30.
Which has the bigger context window?
Granite 4.0 Micro does, with 131K tokens against 128K.
How many benchmarks do Devstral Small 2505 and Granite 4.0 Micro share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Granite 4.0 Micro has 8.