Model comparison
Qwen2-72B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 29.5 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. Qwen2-72B scores higher in 1 category and Tulu 3 (Tülu 3) 70B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 27.9 to 13.3.
- The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 46.3% for Tulu 3 (Tülu 3) 70B.
Side by side
| Qwen2-72B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Allen Institute for AI (Ai2) |
| Noometry Index | 29.5 | 32.6 |
| Released | 2024-06-07 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 26 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Qwen2-72B: 28.7 (#303), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1196 | 1236 |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 16.9 (#138), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Too close to call
Qwen2-72B: 22.2 (#184), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1220 |
| Epoch Capabilities Index | 125.27 | — |
Math Qwen2-72B leads
Qwen2-72B: 27.9 (#232), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1235 | 1242 |
| MATH Level 5 | 39.1% | 42.7% |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Qwen2-72B: 21.2 (#270), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 40.8% | 46.3% |
| LMArena Expert | 1171 | — |
| MMLU | 82.4% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Qwen2-72B: 36.0 (#239), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1176 | 1236 |
| LMArena Chinese | 1240 | 1249 |
| LMArena Russian | 1169 | 1246 |
| LMArena French | 1169 | — |
| LMArena German | 1151 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1083 | — |
| LMArena Spanish | 1168 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Qwen2-72B: 62.0 (#236), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1181 | 1233 |
Long Context Too close to call
Qwen2-72B: 36.1 (#230), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1193 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Qwen2-72B: 41.0 (#236), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Qwen2-72B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1203 | 1256 |
| LMArena Creative Writing | 1181 | 1231 |
| LMArena Multi-Turn | 1195 | 1252 |
Frequently asked questions
Is Qwen2-72B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 29.5 on the Noometry Index.
Is Qwen2-72B or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 28.7 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.