Model comparison
Granite 4.0 H Small vs Llama 3-8B
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 25.5 on the Noometry Index.
Last verified . 13 shared benchmarks.
MetaSummary
- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.0 H Small leads 32.0 to 7.8.
Side by side
| Granite 4.0 H Small | Llama 3-8B | |
|---|---|---|
| Provider | IBM | Meta |
| Noometry Index | 36.5 | 25.5 |
| Released | — | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 34 |
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), Llama 3-8B: 31.0 (#289)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1249 | 1152 |
| BigCodeBench Instruct | — | 31.9% |
| BigCodeBench Complete | — | 36.9% |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 24.4 (#163), Llama 3-8B: 14.3 (#326)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1133 |
| Chess Puzzles | — | 0% |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| Epoch Capabilities Index | — | 116.45 |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 31.4 (#223), Llama 3-8B: 8.8 (#323)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Math | 1247 | 1151 |
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| Omni-MATH | 29.6% | — |
| MATH Level 5 | — | 6.1% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 32.0 (#215), Llama 3-8B: 7.8 (#308)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Expert | 1251 | 1113 |
| GPQA Diamond | — | 26.1% |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Granite 4.0 H Small leads
Granite 4.0 H Small: 38.6 (#228), Llama 3-8B: 30.8 (#261)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1216 | 1098 |
| LMArena Chinese | 1249 | 1076 |
| LMArena Russian | 1201 | 1109 |
| LMArena Spanish | 1258 | 1173 |
| LMArena French | — | 1159 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1004 |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.7 (#183), Llama 3-8B: 58.4 (#260)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1222 | 1127 |
| IFEval | 89% | — |
Long Context Granite 4.0 H Small leads
Granite 4.0 H Small: 37.7 (#213), Llama 3-8B: 34.2 (#251)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1242 | 1128 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 43.8 (#227), Llama 3-8B: 37.5 (#256)
| Benchmark | Granite 4.0 H Small | Llama 3-8B |
|---|---|---|
| LMArena Text | 1241 | 1166 |
| LMArena Creative Writing | 1211 | 1150 |
| LMArena Multi-Turn | 1242 | 1152 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Llama 3-8B?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 25.5 on the Noometry Index.
Is Granite 4.0 H Small or Llama 3-8B better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 31.0 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Llama 3-8B share?
13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Llama 3-8B has 34.