Model comparison
Devstral Small 2505 vs Granite 4.0 H Small
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 33.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where Granite 4.0 H Small leads 23.4 to 19.1.
Side by side
| Devstral Small 2505 | Granite 4.0 H Small | |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 33.9 | 35.9 |
| Released | 2025-05-07 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Devstral Small 2505: 38.6 (#160), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1247 |
Reasoning Granite 4.0 H Small leads
Devstral Small 2505: 19.1 (#243), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1240 |
Math Not comparable
Devstral Small 2505: —, Granite 4.0 H Small: 29.3 (#219)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| Omni-MATH | — | 29.6% |
| LMArena Math | — | 1251 |
Knowledge Not comparable
Devstral Small 2505: —, Granite 4.0 H Small: 31.5 (#210)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
| LMArena Expert | — | 1244 |
Multilingual Not comparable
Devstral Small 2505: —, Granite 4.0 H Small: 38.7 (#223)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | — | 1216 |
| LMArena Chinese | — | 1250 |
| LMArena Russian | — | 1198 |
| LMArena Spanish | — | 1258 |
Instruction Following Not comparable
Devstral Small 2505: —, Granite 4.0 H Small: 68.9 (#178)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| IFEval | — | 89% |
| LMArena Instruction Following | — | 1221 |
Long Context Not comparable
Devstral Small 2505: —, Granite 4.0 H Small: 37.6 (#209)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | — | 1240 |
Writing & Preference Not comparable
Devstral Small 2505: —, Granite 4.0 H Small: 44.0 (#222)
| Benchmark | Devstral Small 2505 | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | — | 1241 |
| LMArena Creative Writing | — | 1210 |
| WildBench | — | 73.9% |
| LMArena Multi-Turn | — | 1243 |
Frequently asked questions
Is Devstral Small 2505 better than Granite 4.0 H Small?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 33.9 on the Noometry Index.
Is Devstral Small 2505 or Granite 4.0 H Small better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 35.8 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and Granite 4.0 H Small share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Granite 4.0 H Small has 19.