Model comparison
Granite 4.0 Micro vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 28.8 on the Noometry Index.
Last verified . 2 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 2 benchmarks with published results for both. Granite 4.0 Micro scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Tulu 3 (Tülu 3) 70B leads 25.1 to 9.9.
- The biggest single-benchmark swing is GPQA Diamond: 28.3% for Granite 4.0 Micro and 46.3% for Tulu 3 (Tülu 3) 70B.
Side by side
| Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | IBM | Allen Institute for AI (Ai2) |
| Noometry Index | 28.8 | 32.6 |
| Released | 2025-10-02 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.017 | — |
| Output $ / M tokens | $0.11 | — |
| Results tracked | 8 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 Micro: —, Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | — | 1236 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Granite 4.0 Micro: 18.5 (#261), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1220 |
Math Tulu 3 (Tülu 3) 70B leads
Granite 4.0 Micro: 11.2 (#301), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | 4.4% |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Granite 4.0 Micro: 9.9 (#299), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 28.3% | 46.3% |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
Multilingual Not comparable
Granite 4.0 Micro: —, Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Granite 4.0 Micro leads
Granite 4.0 Micro: 70.0 (#164), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
Granite 4.0 Micro: —, Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Too close to call
Granite 4.0 Micro: 46.7 (#212), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Granite 4.0 Micro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| WildBench | 67% | — |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Granite 4.0 Micro better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 28.8 on the Noometry Index.
How many benchmarks do Granite 4.0 Micro and Tulu 3 (Tülu 3) 70B share?
2 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.