Model comparison
Qwen3-4B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 31.5 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. Qwen3-4B scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-4B leads 28.5 to 13.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 52.2% for Qwen3-4B and 4.4% for Tulu 3 (Tülu 3) 70B.
Side by side
| Qwen3-4B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Allen Institute for AI (Ai2) |
| Noometry Index | 31.5 | 32.6 |
| Released | 2025-04-29 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 6 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3-4B: —, Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | — | 1236 |
Agentic & Tool Use Not comparable
Qwen3-4B: 27.3 (#94), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 35.7% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Qwen3-4B: 18.5 (#264), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | — | 1220 |
Math Qwen3-4B leads
Qwen3-4B: 28.5 (#228), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 52.2% | 4.4% |
| MathArena Final-Answer Competitions | 38.5% | — |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Qwen3-4B leads
Qwen3-4B: 33.0 (#198), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 52.3% | 46.3% |
| Vectara Hallucination Rate | 5.7% | — |
Multilingual Not comparable
Qwen3-4B: —, Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Not comparable
Qwen3-4B: —, Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
Qwen3-4B: —, Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Not comparable
Qwen3-4B: —, Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Qwen3-4B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Qwen3-4B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 31.5 on the Noometry Index.
How many benchmarks do Qwen3-4B and Tulu 3 (Tülu 3) 70B share?
2 benchmarks have published results for both models. Qwen3-4B has 6 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.