Model comparison
Granite 4.2 3b vs Tulu 3 (Tülu 3) 70B
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 32.6 on the Noometry Index.
Last verified . 10 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. Granite 4.2 3b scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 3b leads 35.6 to 25.1.
Side by side
| Granite 4.2 3b | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | IBM | Allen Institute for AI (Ai2) |
| Noometry Index | 39.0 | 32.6 |
| Released | — | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 3b leads
Granite 4.2 3b: 39.4 (#146), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1363 | 1236 |
Reasoning Granite 4.2 3b leads
Granite 4.2 3b: 25.0 (#136), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1308 | 1220 |
Math Not comparable
Granite 4.2 3b: —, Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Granite 4.2 3b leads
Granite 4.2 3b: 35.6 (#169), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1313 | — |
Multilingual Granite 4.2 3b leads
Granite 4.2 3b: 42.4 (#193), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1268 | 1236 |
| LMArena Chinese | 1268 | 1249 |
| LMArena Russian | 1249 | 1246 |
Instruction Following Granite 4.2 3b leads
Granite 4.2 3b: 67.2 (#195), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1271 | 1233 |
Long Context Granite 4.2 3b leads
Granite 4.2 3b: 39.3 (#179), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1293 | 1224 |
Writing & Preference Granite 4.2 3b leads
Granite 4.2 3b: 47.9 (#202), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Granite 4.2 3b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1295 | 1256 |
| LMArena Creative Writing | 1215 | 1231 |
| LMArena Multi-Turn | 1293 | 1252 |
Frequently asked questions
Is Granite 4.2 3b better than Tulu 3 (Tülu 3) 70B?
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 32.6 on the Noometry Index.
Is Granite 4.2 3b or Tulu 3 (Tülu 3) 70B better for coding?
Granite 4.2 3b scores higher on coding benchmarks: 39.4 versus 35.4 in the Noometry coding category.
How many benchmarks do Granite 4.2 3b and Tulu 3 (Tülu 3) 70B share?
10 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.