Model comparison
Granite 3.0 2b Instruct vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 30.8 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 3.0 2b Instruct scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.0 2b Instruct leads 32.2 to 14.2.
Side by side
| Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | IBM | Allen Institute for AI (Ai2) |
| Noometry Index | 30.8 | 33.0 |
| Released | — | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Granite 3.0 2b Instruct: 28.3 (#316), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1090 | 1235 |
| BigCodeBench Instruct | 20.5% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Granite 3.0 2b Instruct: 20.5 (#235), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1220 |
Math Granite 3.0 2b Instruct leads
Granite 3.0 2b Instruct: 32.2 (#217), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1117 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Granite 3.0 2b Instruct leads
Granite 3.0 2b Instruct: 29.0 (#241), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1064 | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Granite 3.0 2b Instruct: 27.0 (#278), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1033 | 1236 |
| LMArena Chinese | 1070 | 1249 |
| LMArena Russian | 1045 | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Granite 3.0 2b Instruct: 53.9 (#284), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1056 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Granite 3.0 2b Instruct: 32.5 (#268), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1070 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Granite 3.0 2b Instruct: 29.6 (#292), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Granite 3.0 2b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1080 | 1256 |
| LMArena Creative Writing | 1046 | 1231 |
| LMArena Multi-Turn | 1053 | 1252 |
Frequently asked questions
Is Granite 3.0 2b Instruct better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 30.8 on the Noometry Index.
Is Granite 3.0 2b Instruct or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 28.3 in the Noometry coding category.
How many benchmarks do Granite 3.0 2b Instruct and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.