Model comparison
Qwen1.5-7B vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 38.8 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Qwen1.5-7B scores higher in 0 categories and Qwen3 32B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 53.1 to 29.8.
Side by side
| Qwen1.5-7B | Qwen3 32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 38.8 |
| Released | 2024-02-04 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 13 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Qwen1.5-7B: 31.6 (#271), Qwen3 32B: 37.3 (#184)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1107 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Qwen1.5-7B: —, Qwen3 32B: 32.3 (#58)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Too close to call
Qwen1.5-7B: 19.5 (#237), Qwen3 32B: 19.6 (#233)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1066 | 1335 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Qwen1.5-7B: 29.0 (#222), Qwen3 32B: 37.9 (#89)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Math | 1080 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
Knowledge Qwen3 32B leads
Qwen1.5-7B: 28.2 (#239), Qwen3 32B: 40.0 (#112)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Expert | 1055 | 1362 |
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| MMLU | 62.6% | — |
Multilingual Qwen3 32B leads
Qwen1.5-7B: 28.6 (#266), Qwen3 32B: 45.8 (#162)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1058 | 1317 |
| LMArena Chinese | 1140 | 1357 |
| LMArena Russian | 1006 | 1311 |
| LMArena German | — | 1341 |
Instruction Following Qwen3 32B leads
Qwen1.5-7B: 54.4 (#276), Qwen3 32B: 69.1 (#174)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1058 | 1305 |
Long Context Qwen3 32B leads
Qwen1.5-7B: 33.1 (#261), Qwen3 32B: 43.7 (#83)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1090 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Qwen1.5-7B: 29.8 (#288), Qwen3 32B: 53.1 (#158)
| Benchmark | Qwen1.5-7B | Qwen3 32B |
|---|---|---|
| LMArena Text | 1084 | 1340 |
| LMArena Creative Writing | 1035 | 1297 |
| LMArena Multi-Turn | 1061 | 1331 |
Frequently asked questions
Is Qwen1.5-7B better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 30.8 on the Noometry Index.
Is Qwen1.5-7B or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.3 versus 31.6 in the Noometry coding category.
How many benchmarks do Qwen1.5-7B and Qwen3 32B share?
12 benchmarks have published results for both models. Qwen1.5-7B has 13 scored results on Noometry and Qwen3 32B has 26.