Model comparison
Granite 4.0 H Small vs Mistral Medium
Granite 4.0 H Small and Mistral Medium score almost the same on the Noometry Index (36.5 vs 36.3), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
Mistral AISummary
- They share 14 benchmarks with published results for both. Granite 4.0 H Small scores higher in 4 categories and Mistral Medium in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 43.8.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.2% for Granite 4.0 H Small and 22.7% for Mistral Medium.
Side by side
| Granite 4.0 H Small | Mistral Medium | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 36.5 | 36.3 |
| Released | — | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 19 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Granite 4.0 H Small: 36.4 (#209), Mistral Medium: 34.2 (#243)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Coding | 1249 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Granite 4.0 H Small: —, Mistral Medium: 28.3 (#90)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Too close to call
Granite 4.0 H Small: 24.4 (#163), Mistral Medium: 24.0 (#167)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 31.4 (#223), Mistral Medium: 28.1 (#245)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Math | 1247 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| Omni-MATH | 29.6% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 32.0 (#215), Mistral Medium: 25.0 (#265)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| Vectara Hallucination Rate | 5.2% | 22.7% |
| LMArena Expert | 1251 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| MMLU-Pro | 56.9% | — |
| GPQA (HELM) | 38.3% | — |
Multimodal Not comparable
Granite 4.0 H Small: —, Mistral Medium: 35.3 (#88)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Granite 4.0 H Small: 38.6 (#228), Mistral Medium: 52.1 (#91)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1216 | 1408 |
| LMArena Chinese | 1249 | 1447 |
| LMArena Russian | 1201 | 1411 |
| LMArena Spanish | 1258 | 1433 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
Instruction Following Mistral Medium leads
Granite 4.0 H Small: 68.7 (#183), Mistral Medium: 73.7 (#116)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1222 | 1398 |
| IFEval | 89% | — |
Long Context Mistral Medium leads
Granite 4.0 H Small: 37.7 (#213), Mistral Medium: 42.9 (#114)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1242 | 1406 |
Writing & Preference Mistral Medium leads
Granite 4.0 H Small: 43.8 (#227), Mistral Medium: 60.0 (#103)
| Benchmark | Granite 4.0 H Small | Mistral Medium |
|---|---|---|
| LMArena Text | 1241 | 1424 |
| LMArena Creative Writing | 1211 | 1391 |
| LMArena Multi-Turn | 1242 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Mistral Medium?
Granite 4.0 H Small and Mistral Medium score almost the same on the Noometry Index (36.5 vs 36.3), so choose on price, context window or the category you care about most.
Is Granite 4.0 H Small or Mistral Medium better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 34.2 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Mistral Medium share?
14 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Mistral Medium has 36.