Model comparison
Qwen1.5-32B vs Qwen3-4B
Qwen3-4B is the stronger model overall, scoring 31.5 to 30.0 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Qwen1.5-32B scores higher in 2 categories and Qwen3-4B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 30.7% for Qwen1.5-32B and 52.3% for Qwen3-4B.
Side by side
| Qwen1.5-32B | Qwen3-4B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.0 | 31.5 |
| Released | 2024-02-04 | 2025-04-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen1.5-32B: 31.1 (#278), Qwen3-4B: —
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| BigCodeBench Instruct | 32.3% | — |
| LMArena Coding | 1155 | — |
| BigCodeBench Complete | 42% | — |
Agentic & Tool Use Not comparable
Qwen1.5-32B: —, Qwen3-4B: 27.3 (#94)
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Qwen1.5-32B leads
Qwen1.5-32B: 20.9 (#210), Qwen3-4B: 18.5 (#264)
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1131 | — |
Math Qwen1.5-32B leads
Qwen1.5-32B: 30.5 (#207), Qwen3-4B: 28.5 (#228)
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| LMArena Math | 1155 | — |
Knowledge Qwen3-4B leads
Qwen1.5-32B: 13.5 (#291), Qwen3-4B: 33.0 (#198)
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 30.7% | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1126 | — |
| MMLU | 74.4% | — |
Multilingual Not comparable
Qwen1.5-32B: 31.6 (#254), Qwen3-4B: —
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1106 | — |
| LMArena Chinese | 1176 | — |
| LMArena French | 1100 | — |
| LMArena German | 1058 | — |
| LMArena Japanese | 1027 | — |
| LMArena Korean | 1007 | — |
| LMArena Russian | 1073 | — |
| LMArena Spanish | 1089 | — |
Instruction Following Not comparable
Qwen1.5-32B: 58.0 (#260), Qwen3-4B: —
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1116 | — |
Long Context Not comparable
Qwen1.5-32B: 34.7 (#241), Qwen3-4B: —
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1146 | — |
Writing & Preference Not comparable
Qwen1.5-32B: 34.4 (#266), Qwen3-4B: —
| Benchmark | Qwen1.5-32B | Qwen3-4B |
|---|---|---|
| LMArena Text | 1137 | — |
| LMArena Creative Writing | 1083 | — |
| LMArena Multi-Turn | 1140 | — |
Frequently asked questions
Is Qwen1.5-32B better than Qwen3-4B?
Qwen3-4B is the stronger model overall, scoring 31.5 to 30.0 on the Noometry Index.
How many benchmarks do Qwen1.5-32B and Qwen3-4B share?
1 benchmark has published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Qwen3-4B has 6.