Model comparison
Granite 4.0 H Small vs Yi-34B
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 27.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 8 categories and Yi-34B 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 7.5.
Side by side
| Granite 4.0 H Small | Yi-34B | |
|---|---|---|
| Provider | IBM | 01.AI |
| Noometry Index | 36.5 | 27.8 |
| Released | — | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 23 |
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), Yi-34B: 32.3 (#274)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Coding | 1249 | 1112 |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 24.4 (#163), Yi-34B: 21.2 (#226)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 31.4 (#223), Yi-34B: 21.6 (#282)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Math | 1247 | 1114 |
| Omni-MATH | 29.6% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 32.0 (#215), Yi-34B: 7.5 (#309)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Expert | 1251 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | — | 76.3% |
Multilingual Granite 4.0 H Small leads
Granite 4.0 H Small: 38.6 (#228), Yi-34B: 29.7 (#264)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Non-English | 1216 | 1079 |
| LMArena Chinese | 1249 | 1176 |
| LMArena Russian | 1201 | 1050 |
| LMArena Spanish | 1258 | 1070 |
| LMArena French | — | 1081 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.7 (#183), Yi-34B: 56.2 (#274)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1222 | 1091 |
| IFEval | 89% | — |
Long Context Granite 4.0 H Small leads
Granite 4.0 H Small: 37.7 (#213), Yi-34B: 33.2 (#264)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1242 | 1094 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 43.8 (#227), Yi-34B: 34.1 (#273)
| Benchmark | Granite 4.0 H Small | Yi-34B |
|---|---|---|
| LMArena Text | 1241 | 1129 |
| LMArena Creative Writing | 1211 | 1108 |
| LMArena Multi-Turn | 1242 | 1113 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Yi-34B?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 27.8 on the Noometry Index.
Is Granite 4.0 H Small or Yi-34B better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 32.3 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Yi-34B share?
13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Yi-34B has 23.