Model comparison
Llama 13b 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 . 8 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 1 category and Tulu 3 (Tülu 3) 70B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 13.8.
Side by side
| Llama 13b | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 24.4 | 33.0 |
| Released | 2023-02-24 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Llama 13b: 21.4 (#337), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 683 | 1235 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Llama 13b: 14.0 (#329), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1220 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Llama 13b leads
Llama 13b: 26.7 (#256), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 838 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Tulu 3 (Tülu 3) 70B: —
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Llama 13b: 16.6 (#297), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 819 | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Llama 13b: 36.7 (#305), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 781 | 1233 |
Long Context Not comparable
Llama 13b: —, Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Llama 13b: 13.8 (#312), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Llama 13b | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 834 | 1256 |
| LMArena Creative Writing | 794 | 1231 |
| LMArena Multi-Turn | 753 | 1252 |
Frequently asked questions
Is Llama 13b 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 13b or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Tulu 3 (Tülu 3) 70B share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.