Model comparison
Qwen2.5-Max vs Tulu 3 (Tülu 3) 70B
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Qwen2.5-Max scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 36.9 to 14.2.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-Max | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Allen Institute for AI (Ai2) |
| Noometry Index | 40.7 | 33.0 |
| Released | 2025-01-25 | 2024-11-21 |
| Weights | Proprietary | 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 Qwen2.5-Max leads
Qwen2.5-Max: 41.8 (#117), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1359 | 1235 |
| LiveBench Coding | 64.4% | — |
Reasoning Qwen2.5-Max leads
Qwen2.5-Max: 25.6 (#147), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1220 |
| LiveBench Reasoning | 51.4% | — |
| LiveBench Data Analysis | 67.9% | — |
| Epoch Capabilities Index | 132.53 | — |
| LiveBench | 62.3% | — |
Math Qwen2.5-Max leads
Qwen2.5-Max: 36.9 (#162), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1369 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LiveBench Math | 58.4% | — |
| MATH Level 5 | — | 42.7% |
Knowledge Qwen2.5-Max leads
Qwen2.5-Max: 35.3 (#186), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Confabulations | 21.8% | — |
| LMArena Expert | 1337 | — |
Multilingual Qwen2.5-Max leads
Qwen2.5-Max: 48.1 (#146), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1352 | 1236 |
| LMArena Chinese | 1382 | 1249 |
| LMArena Russian | 1353 | 1246 |
| LMArena French | 1396 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1300 | — |
| LMArena Korean | 1304 | — |
| LMArena Spanish | 1377 | — |
Instruction Following Qwen2.5-Max leads
Qwen2.5-Max: 71.3 (#152), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1335 | 1233 |
| LiveBench Instruction Following | 75.3% | — |
Long Context Qwen2.5-Max leads
Qwen2.5-Max: 41.4 (#142), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1358 | 1224 |
Writing & Preference Qwen2.5-Max leads
Qwen2.5-Max: 55.4 (#146), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Qwen2.5-Max | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1367 | 1256 |
| LMArena Creative Writing | 1339 | 1231 |
| LMArena Multi-Turn | 1364 | 1252 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |
Frequently asked questions
Is Qwen2.5-Max better than Tulu 3 (Tülu 3) 70B?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 33.0 on the Noometry Index.
Is Qwen2.5-Max or Tulu 3 (Tülu 3) 70B better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 36.0 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.