Model comparison
Gemma 7B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 30.0 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 7B 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 writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 27.1.
Side by side
| Gemma 7B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 30.0 | 33.0 |
| Released | 2024-02-21 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Gemma 7B: 30.5 (#294), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1048 | 1235 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Gemma 7B: 19.9 (#249), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1220 |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.99 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Gemma 7B leads
Gemma 7B: 31.2 (#228), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1066 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
| GSM8K | 46.4% | — |
Knowledge Gemma 7B leads
Gemma 7B: 27.3 (#252), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1001 | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Gemma 7B: 25.1 (#287), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 999 | 1236 |
| LMArena Chinese | 1035 | 1249 |
| LMArena Russian | 993 | 1246 |
| LMArena French | 1025 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Gemma 7B: 51.5 (#295), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1017 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Gemma 7B: 31.1 (#282), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1022 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Gemma 7B: 27.1 (#302), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Gemma 7B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1056 | 1256 |
| LMArena Creative Writing | 1024 | 1231 |
| LMArena Multi-Turn | 963 | 1252 |
Frequently asked questions
Is Gemma 7B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 30.0 on the Noometry Index.
Is Gemma 7B or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.