Model comparison
Llama 2-70B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 24.4 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Tulu 3 (Tülu 3) 70B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Tulu 3 (Tülu 3) 70B leads 25.0 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 42.7% for Tulu 3 (Tülu 3) 70B.
Side by side
| Llama 2-70B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 24.4 | 33.0 |
| Released | 2023-07-18 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 31.4 (#286), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1079 | 1235 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 14.4 (#325), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1220 |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 8.1 (#326), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 4.4% |
| LMArena Math | 1091 | 1242 |
| MATH Level 5 | 3.3% | 42.7% |
| GSM8K | 69.6% | — |
Knowledge Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 7.4 (#310), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 26.3% | 46.3% |
| LMArena Expert | 1039 | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 27.7 (#274), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1045 | 1236 |
| LMArena Chinese | 995 | 1249 |
| LMArena Russian | 1083 | 1246 |
| LMArena French | 1090 | — |
| LMArena German | 1041 | — |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 54.9 (#278), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1071 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 32.3 (#270), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1062 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Llama 2-70B: 32.3 (#279), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Llama 2-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1115 | 1256 |
| LMArena Creative Writing | 1075 | 1231 |
| LMArena Multi-Turn | 1088 | 1252 |
Frequently asked questions
Is Llama 2-70B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 24.4 on the Noometry Index.
Is Llama 2-70B or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.