Model comparison
Qwen3 14B vs Tulu 3 (Tülu 3) 70B
Qwen3 14B is the stronger model overall, scoring 35.5 to 33.0 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. Qwen3 14B scores higher in 4 categories and Tulu 3 (Tülu 3) 70B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 14B leads 38.6 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for Qwen3 14B and 4.4% for Tulu 3 (Tülu 3) 70B.
Side by side
| Qwen3 14B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Allen Institute for AI (Ai2) |
| Noometry Index | 35.5 | 33.0 |
| Released | 2025-04 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $1.40 | — |
| Results tracked | 12 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 14B leads
Qwen3 14B: 37.3 (#195), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| SciCode | 31.6% | — |
| LMArena Coding | — | 1235 |
Agentic & Tool Use Not comparable
Qwen3 14B: 29.6 (#83), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Qwen3 14B: 18.5 (#280), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Kagi LLM Benchmark | 49.1% | — |
| CritPt | 0% | — |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | — | 1220 |
| DTBench | 64% | — |
| LMCA | 18.2% | — |
| Epoch Capabilities Index | 138.23 | — |
Math Qwen3 14B leads
Qwen3 14B: 38.6 (#133), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 4.4% |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Qwen3 14B leads
Qwen3 14B: 39.3 (#134), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 63.8% | 46.3% |
| Vectara Hallucination Rate | 5.4% | — |
Multilingual Not comparable
Qwen3 14B: —, Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Not comparable
Qwen3 14B: —, Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | — | 1233 |
Long Context Too close to call
Qwen3 14B: 38.1 (#204), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Fiction.LiveBench | 62.5% | — |
| LMArena Longer Query | — | 1224 |
Writing & Preference Not comparable
Qwen3 14B: —, Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Qwen3 14B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Qwen3 14B better than Tulu 3 (Tülu 3) 70B?
Qwen3 14B is the stronger model overall, scoring 35.5 to 33.0 on the Noometry Index.
Is Qwen3 14B or Tulu 3 (Tülu 3) 70B better for coding?
Qwen3 14B scores higher on coding benchmarks: 37.3 versus 36.0 in the Noometry coding category.
How many benchmarks do Qwen3 14B and Tulu 3 (Tülu 3) 70B share?
2 benchmarks have published results for both models. Qwen3 14B has 12 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.