Model comparison
Llama 3-70B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 28.8 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 3-70B scores higher in 0 categories and Tulu 3 (Tülu 3) 70B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Tulu 3 (Tülu 3) 70B leads 39.9 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 22.6% for Llama 3-70B and 42.7% for Tulu 3 (Tülu 3) 70B.
Side by side
| Llama 3-70B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 28.8 | 33.0 |
| Released | 2024-04-18 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-70B: 35.8 (#218), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1206 | 1235 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Cybench | 5% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Llama 3-70B: 18.0 (#288), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1220 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Tulu 3 (Tülu 3) 70B leads
Llama 3-70B: 12.8 (#305), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 4.4% |
| LMArena Math | 1218 | 1242 |
| MATH Level 5 | 22.6% | 42.7% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Llama 3-70B: 20.8 (#277), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 40.6% | 46.3% |
| LMArena Expert | 1149 | — |
| MMLU | 79.3% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Llama 3-70B: 33.6 (#251), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1142 | 1236 |
| LMArena Chinese | 1114 | 1249 |
| LMArena Russian | 1159 | 1246 |
| LMArena French | 1232 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Llama 3-70B: 62.5 (#238), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1194 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Llama 3-70B: 35.6 (#240), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1174 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Llama 3-70B: 42.8 (#231), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Llama 3-70B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1221 | 1256 |
| LMArena Creative Writing | 1210 | 1231 |
| LMArena Multi-Turn | 1223 | 1252 |
Frequently asked questions
Is Llama 3-70B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 28.8 on the Noometry Index.
Is Llama 3-70B or Tulu 3 (Tülu 3) 70B better for coding?
They score almost the same on coding (35.8 vs 36.0); test both on your own repository before choosing.
How many benchmarks do Llama 3-70B and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.