Model comparison
Granite 4.0 H Small vs Mistral Small 3.1
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 31.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. Granite 4.0 H Small scores higher in 5 categories and Mistral Small 3.1 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 4.0 H Small leads 31.4 to 14.7.
- The biggest single-benchmark swing is IFEval: 89% for Granite 4.0 H Small and 75% for Mistral Small 3.1.
Side by side
| Granite 4.0 H Small | Mistral Small 3.1 | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 36.5 | 31.7 |
| Released | — | 2025-03-17 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 102K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $0.56 |
| Results tracked | 19 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Granite 4.0 H Small: 36.4 (#209), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1249 | 1309 |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 24.4 (#163), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1278 |
| Chess Puzzles | — | 1% |
| Epoch Capabilities Index | — | 127.48 |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 31.4 (#223), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| Omni-MATH | 29.6% | 24.8% |
| LMArena Math | 1247 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 3.9% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 32.0 (#215), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| MMLU-Pro | 56.9% | 61% |
| GPQA (HELM) | 38.3% | 39.2% |
| LMArena Expert | 1251 | 1257 |
| GPQA Diamond | — | 41.9% |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Not comparable
Granite 4.0 H Small: —, Mistral Small 3.1: 33.2 (#99)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual Mistral Small 3.1 leads
Granite 4.0 H Small: 38.6 (#228), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1216 | 1255 |
| LMArena Chinese | 1249 | 1253 |
| LMArena Russian | 1201 | 1263 |
| LMArena Spanish | 1258 | 1283 |
| LMArena French | — | 1273 |
| LMArena German | — | 1266 |
| LMArena Japanese | — | 1208 |
| LMArena Korean | — | 1206 |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.7 (#183), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| IFEval | 89% | 75% |
| LMArena Instruction Following | 1222 | 1264 |
Long Context Mistral Small 3.1 leads
Granite 4.0 H Small: 37.7 (#213), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1242 | 1299 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 43.8 (#227), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Granite 4.0 H Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1241 | 1277 |
| LMArena Creative Writing | 1211 | 1253 |
| WildBench | 73.9% | 78.8% |
| LMArena Multi-Turn | 1242 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
Frequently asked questions
Is Granite 4.0 H Small better than Mistral Small 3.1?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 31.7 on the Noometry Index.
Is Granite 4.0 H Small or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 36.4 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Mistral Small 3.1 share?
18 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Mistral Small 3.1 has 28.