Model comparison
Qwen3 14B vs Qwen3-4B
Qwen3 14B is the stronger model overall, scoring 35.5 to 31.9 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Qwen3 14B scores higher in 3 categories and Qwen3-4B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 14B leads 38.6 to 29.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for Qwen3 14B and 52.2% for Qwen3-4B.
Side by side
| Qwen3 14B | Qwen3-4B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 35.5 | 31.9 |
| Released | 2025-04 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $1.40 | — |
| Results tracked | 12 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3 14B: 37.3 (#195), Qwen3-4B: —
| Benchmark | Qwen3 14B | Qwen3-4B |
|---|---|---|
| SciCode | 31.6% | — |
Agentic & Tool Use Qwen3 14B leads
Qwen3 14B: 29.6 (#83), Qwen3-4B: 27.6 (#100)
| Benchmark | Qwen3 14B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41% | 35.7% |
Reasoning Too close to call
Qwen3 14B: 18.5 (#280), Qwen3-4B: 19.2 (#268)
| Benchmark | Qwen3 14B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 4% | 4% |
| Kagi LLM Benchmark | 49.1% | — |
| CritPt | 0% | — |
| DTBench | 64% | — |
| LMCA | 18.2% | — |
| Epoch Capabilities Index | 138.23 | — |
Math Qwen3 14B leads
Qwen3 14B: 38.6 (#133), Qwen3-4B: 29.7 (#240)
| Benchmark | Qwen3 14B | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 52.2% |
| MathArena Final-Answer Competitions | — | 38.5% |
Knowledge Qwen3 14B leads
Qwen3 14B: 39.3 (#134), Qwen3-4B: 33.0 (#208)
| Benchmark | Qwen3 14B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 63.8% | 52.3% |
| Vectara Hallucination Rate | 5.4% | 5.7% |
Long Context Not comparable
Qwen3 14B: 38.1 (#204), Qwen3-4B: —
| Benchmark | Qwen3 14B | Qwen3-4B |
|---|---|---|
| Fiction.LiveBench | 62.5% | — |
Frequently asked questions
Is Qwen3 14B better than Qwen3-4B?
Qwen3 14B is the stronger model overall, scoring 35.5 to 31.9 on the Noometry Index.
How many benchmarks do Qwen3 14B and Qwen3-4B share?
5 benchmarks have published results for both models. Qwen3 14B has 12 scored results on Noometry and Qwen3-4B has 6.