Model comparison
Granite 4.0 H Small vs Mixtral 8x7B
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 26.8 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 8 categories and Mixtral 8x7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.0 H Small leads 31.5 to 11.0.
- The biggest single-benchmark swing is IFEval: 89% for Granite 4.0 H Small and 57.5% for Mixtral 8x7B.
Side by side
| Granite 4.0 H Small | Mixtral 8x7B | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 35.9 | 26.8 |
| Released | — | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 32K |
| Max output | — | 32K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 19 | 38 |
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: 35.8 (#207), Mixtral 8x7B: 32.2 (#265)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1247 | 1127 |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 23.4 (#164), Mixtral 8x7B: 17.4 (#283)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1115 |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| Epoch Capabilities Index | — | 118.38 |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 29.3 (#219), Mixtral 8x7B: 17.2 (#284)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | 29.6% | 10.5% |
| LMArena Math | 1251 | 1147 |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 31.5 (#210), Mixtral 8x7B: 11.0 (#296)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| MMLU-Pro | 56.9% | 33.5% |
| GPQA (HELM) | 38.3% | 29.6% |
| LMArena Expert | 1244 | 1088 |
| GPQA Diamond | — | 30.6% |
| Vectara Hallucination Rate | 5.2% | — |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual Granite 4.0 H Small leads
Granite 4.0 H Small: 38.7 (#223), Mixtral 8x7B: 29.8 (#261)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1216 | 1077 |
| LMArena Chinese | 1250 | 1055 |
| LMArena Russian | 1198 | 1090 |
| LMArena Spanish | 1258 | 1110 |
| LMArena French | — | 1165 |
| LMArena German | — | 1114 |
| LMArena Japanese | — | 931 |
| LMArena Korean | — | 968 |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.9 (#178), Mixtral 8x7B: 51.2 (#292)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| IFEval | 89% | 57.5% |
| LMArena Instruction Following | 1221 | 1110 |
Long Context Granite 4.0 H Small leads
Granite 4.0 H Small: 37.6 (#209), Mixtral 8x7B: 33.4 (#255)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1240 | 1103 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 44.0 (#222), Mixtral 8x7B: 34.4 (#265)
| Benchmark | Granite 4.0 H Small | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1241 | 1132 |
| LMArena Creative Writing | 1210 | 1109 |
| WildBench | 73.9% | 67.3% |
| LMArena Multi-Turn | 1243 | 1115 |
Frequently asked questions
Is Granite 4.0 H Small better than Mixtral 8x7B?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 26.8 on the Noometry Index.
Is Granite 4.0 H Small or Mixtral 8x7B better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 32.2 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Mixtral 8x7B share?
18 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Mixtral 8x7B has 38.