Model comparison
Granite 4.0 H Small vs Llama 2-13B
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 29.1 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 2-13B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.9 to 53.5.
Side by side
| Granite 4.0 H Small | Llama 2-13B | |
|---|---|---|
| Provider | IBM | Meta |
| Noometry Index | 35.9 | 29.1 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 32 |
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), Llama 2-13B: 30.4 (#287)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1247 | 1062 |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 23.4 (#164), Llama 2-13B: 12.3 (#333)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1051 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 105.8 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Too close to call
Granite 4.0 H Small: 29.3 (#219), Llama 2-13B: 28.7 (#226)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Math | 1251 | 1065 |
| Omni-MATH | 29.6% | — |
| GSM8K | — | 36.9% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 31.5 (#210), Llama 2-13B: 27.5 (#244)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1244 | 1030 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Granite 4.0 H Small: —, Llama 2-13B: —
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Granite 4.0 H Small leads
Granite 4.0 H Small: 38.7 (#223), Llama 2-13B: 26.7 (#274)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1216 | 1024 |
| LMArena Chinese | 1250 | 1001 |
| LMArena Russian | 1198 | 1055 |
| LMArena Spanish | 1258 | 1086 |
| LMArena French | — | 1043 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.9 (#178), Llama 2-13B: 53.5 (#282)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1221 | 1046 |
| IFEval | 89% | — |
Long Context Granite 4.0 H Small leads
Granite 4.0 H Small: 37.6 (#209), Llama 2-13B: 32.3 (#264)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1240 | 1064 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 44.0 (#222), Llama 2-13B: 30.0 (#284)
| Benchmark | Granite 4.0 H Small | Llama 2-13B |
|---|---|---|
| LMArena Text | 1241 | 1085 |
| LMArena Creative Writing | 1210 | 1047 |
| LMArena Multi-Turn | 1243 | 1050 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Llama 2-13B?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 29.1 on the Noometry Index.
Is Granite 4.0 H Small or Llama 2-13B better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 30.4 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Llama 2-13B share?
13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Llama 2-13B has 32.