Model comparison
Gemma 2B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 1 category and Tulu 3 (Tülu 3) 70B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 24.0.
Side by side
| Gemma 2B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 29.6 | 33.0 |
| Released | 2024-02-21 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Gemma 2B: 29.4 (#305), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1010 | 1235 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Gemma 2B: 18.8 (#275), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1220 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Gemma 2B leads
Gemma 2B: 30.0 (#239), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1009 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Gemma 2B: 23.0 (#294), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 958 | 1236 |
| LMArena Chinese | 986 | 1249 |
| LMArena Russian | 937 | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Gemma 2B: 48.5 (#302), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 970 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Gemma 2B: 29.9 (#291), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 981 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Gemma 2B: 24.0 (#308), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Gemma 2B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1002 | 1256 |
| LMArena Creative Writing | 987 | 1231 |
| LMArena Multi-Turn | 945 | 1252 |
Frequently asked questions
Is Gemma 2B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.
Is Gemma 2B or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.