Model comparison
Granite 4.0 H Small vs Tulu 3 (Tülu 3) 70B
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Granite 4.0 H Small scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 4.0 H Small leads 31.4 to 14.2.
Side by side
| Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | IBM | Allen Institute for AI (Ai2) |
| Noometry Index | 36.5 | 33.0 |
| Released | — | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.0 H Small: 36.4 (#209), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1249 | 1235 |
Reasoning Too close to call
Granite 4.0 H Small: 24.4 (#163), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1220 |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 31.4 (#223), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1247 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| Omni-MATH | 29.6% | — |
| MATH Level 5 | — | 42.7% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 32.0 (#215), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1251 | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Granite 4.0 H Small: 38.6 (#228), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1216 | 1236 |
| LMArena Chinese | 1249 | 1249 |
| LMArena Russian | 1201 | 1246 |
| LMArena Spanish | 1258 | — |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.7 (#183), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1222 | 1233 |
| IFEval | 89% | — |
Long Context Too close to call
Granite 4.0 H Small: 37.7 (#213), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1242 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Granite 4.0 H Small: 43.8 (#227), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Granite 4.0 H Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1241 | 1256 |
| LMArena Creative Writing | 1211 | 1231 |
| LMArena Multi-Turn | 1242 | 1252 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Tulu 3 (Tülu 3) 70B?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 33.0 on the Noometry Index.
Is Granite 4.0 H Small or Tulu 3 (Tülu 3) 70B better for coding?
They score almost the same on coding (36.4 vs 36.0); test both on your own repository before choosing.
How many benchmarks do Granite 4.0 H Small and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.