Model comparison
Qwen Plus vs Tulu 3 (Tülu 3) 70B
Qwen Plus is the stronger model overall, scoring 36.7 to 32.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Qwen Plus 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 Qwen Plus leads 22.0 to 13.3.
- The biggest single-benchmark swing is MATH Level 5: 65.3% for Qwen Plus and 42.7% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Qwen Plus | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Allen Institute for AI (Ai2) |
| Noometry Index | 36.7 | 32.6 |
| Released | 2024-01-25 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 20 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Qwen Plus: 38.3 (#163), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1328 | 1236 |
Reasoning Qwen Plus leads
Qwen Plus: 27.6 (#101), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1317 | 1220 |
| Kagi LLM Benchmark | 63.3% | — |
| DTBench | 81.1% | — |
| LMCA | 24% | — |
Math Qwen Plus leads
Qwen Plus: 22.0 (#266), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 17.8% | 4.4% |
| LMArena Math | 1326 | 1242 |
| MATH Level 5 | 65.3% | 42.7% |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Qwen Plus leads
Qwen Plus: 27.4 (#245), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 48.1% | 46.3% |
| LMArena Expert | 1328 | — |
Multilingual Qwen Plus leads
Qwen Plus: 45.3 (#170), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1310 | 1236 |
| LMArena Chinese | 1347 | 1249 |
| LMArena Russian | 1323 | 1246 |
| LMArena Japanese | 1251 | — |
Instruction Following Qwen Plus leads
Qwen Plus: 69.0 (#176), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1303 | 1233 |
Long Context Qwen Plus leads
Qwen Plus: 40.3 (#153), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1325 | 1224 |
Writing & Preference Qwen Plus leads
Qwen Plus: 52.4 (#171), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Qwen Plus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1326 | 1256 |
| LMArena Creative Writing | 1293 | 1231 |
| LMArena Multi-Turn | 1336 | 1252 |
Frequently asked questions
Is Qwen Plus better than Tulu 3 (Tülu 3) 70B?
Qwen Plus is the stronger model overall, scoring 36.7 to 32.6 on the Noometry Index.
Is Qwen Plus or Tulu 3 (Tülu 3) 70B better for coding?
Qwen Plus scores higher on coding benchmarks: 38.3 versus 35.4 in the Noometry coding category.
How many benchmarks do Qwen Plus and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Qwen Plus has 20 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.