Model comparison
Qwen2.5 7B Instruct vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.0 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)
Allen Institute for AI (Ai2)Summary
- They share 2 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Tulu 3 (Tülu 3) 70B leads 23.9 to 14.8.
- The biggest single-benchmark swing is GPQA Diamond: 35.5% for Qwen2.5 7B Instruct and 46.3% for Tulu 3 (Tülu 3) 70B.
Side by side
| Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Allen Institute for AI (Ai2) |
| Noometry Index | 29.0 | 33.0 |
| Released | 2024-09 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.17 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 15 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen2.5 7B Instruct: 36.5 (#208), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1235 |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.8 (#124), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| BALROG | 7.8% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Qwen2.5 7B Instruct: 14.8 (#322), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1220 |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
| Epoch Capabilities Index | 118.51 | — |
Math Tulu 3 (Tülu 3) 70B leads
Qwen2.5 7B Instruct: 12.6 (#306), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 4.4% |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Qwen2.5 7B Instruct: 17.0 (#286), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 35.5% | 46.3% |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| MMLU | 72.9% | — |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Qwen2.5 7B Instruct: 63.2 (#231), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Qwen2.5 7B Instruct leads
Qwen2.5 7B Instruct: 48.8 (#195), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Qwen2.5 7B Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.0 on the Noometry Index.
Is Qwen2.5 7B Instruct or Tulu 3 (Tülu 3) 70B better for coding?
They score almost the same on coding (36.5 vs 36.0); test both on your own repository before choosing.
How many benchmarks do Qwen2.5 7B Instruct and Tulu 3 (Tülu 3) 70B share?
2 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.