Model comparison
Qwen3 32B vs Qwen3-Coder 480B-A35B Instruct
Qwen3 32B is the stronger model overall, scoring 38.8 to 37.7 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Qwen3 32B scores higher in 5 categories and Qwen3-Coder 480B-A35B Instruct in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3 32B leads 32.3 to 23.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 54.9% for Qwen3 32B and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 131K.
Side by side
| Qwen3 32B | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.8 | 37.7 |
| Released | 2025-04 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.70 | $1.50 |
| Output $ / M tokens | $2.80 | $7.50 |
| Results tracked | 26 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Qwen3 32B: 37.3 (#184), Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Coding | 1358 | 1413 |
| SWE-bench Verified (bash only) | — | 55.4% |
| Aider Polyglot | 40% | — |
| LMArena WebDev | — | 1275 |
| SciCode | 35.4% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Qwen3 32B leads
Qwen3 32B: 32.3 (#58), Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | 48.7% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Qwen3 32B: 19.6 (#233), Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 54.9% | 49.5% |
| LMArena Hard Prompts | 1335 | 1372 |
| CritPt | 0.3% | — |
| Chess Puzzles | 5% | — |
| DTBench | 67.5% | — |
| LMCA | 17.3% | — |
| Epoch Capabilities Index | 138.51 | — |
Math Qwen3 32B leads
Qwen3 32B: 37.9 (#89), Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1399 | 1364 |
| OTIS Mock AIME 2024-2025 | 66.9% | — |
Knowledge Qwen3 32B leads
Qwen3 32B: 40.0 (#112), Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1362 | 1337 |
| GPQA Diamond | 65.7% | — |
| Vectara Hallucination Rate | 5.9% | — |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Qwen3 32B: 45.8 (#162), Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1317 | 1345 |
| LMArena Chinese | 1357 | 1356 |
| LMArena German | 1341 | 1324 |
| LMArena Russian | 1311 | 1367 |
| LMArena French | — | 1394 |
| LMArena Japanese | — | 1309 |
| LMArena Korean | — | 1307 |
| LMArena Spanish | — | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Qwen3 32B: 69.1 (#174), Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1305 | 1356 |
Long Context Qwen3 32B leads
Qwen3 32B: 43.7 (#83), Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1327 | 1379 |
| Fiction.LiveBench | 74.2% | — |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Qwen3 32B: 53.1 (#158), Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)
| Benchmark | Qwen3 32B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1340 | 1356 |
| LMArena Creative Writing | 1297 | 1333 |
| LMArena Multi-Turn | 1331 | 1365 |
Frequently asked questions
Is Qwen3 32B better than Qwen3-Coder 480B-A35B Instruct?
Qwen3 32B is the stronger model overall, scoring 38.8 to 37.7 on the Noometry Index.
Which is cheaper, Qwen3 32B or Qwen3-Coder 480B-A35B Instruct?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Qwen3 32B or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.3 versus 36.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 131K.
How many benchmarks do Qwen3 32B and Qwen3-Coder 480B-A35B Instruct share?
14 benchmarks have published results for both models. Qwen3 32B has 26 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.