Model comparison
Qwen2.5 32B Instruct vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 30.1 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Qwen2.5 32B Instruct scores higher in 1 category and Qwen3 32B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 39.7 to 16.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.4% for Qwen2.5 32B Instruct and 66.9% for Qwen3 32B.
- Both cost about the same: $0.70 input and $2.80 output per million tokens.
Side by side
| Qwen2.5 32B Instruct | Qwen3 32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.1 | 39.2 |
| Released | 2024-09 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.70 | $0.70 |
| Output $ / M tokens | $2.80 | $2.80 |
| Results tracked | 7 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
Qwen2.5 32B Instruct: 38.7 (#169), Qwen3 32B: 37.7 (#190)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| BigCodeBench Instruct | 45% | — |
| LMArena Coding | — | 1358 |
| BigCodeBench Complete | 52.3% | — |
Agentic & Tool Use Not comparable
Qwen2.5 32B Instruct: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Too close to call
Qwen2.5 32B Instruct: 19.2 (#266), Qwen3 32B: 20.2 (#241)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| Epoch Capabilities Index | 128.52 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| LMArena Hard Prompts | — | 1334 |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
Math Qwen3 32B leads
Qwen2.5 32B Instruct: 16.2 (#296), Qwen3 32B: 39.7 (#99)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.4% | 66.9% |
| LMArena Math | — | 1399 |
| MATH Level 5 | 56.1% | — |
Knowledge Qwen3 32B leads
Qwen2.5 32B Instruct: 24.9 (#266), Qwen3 32B: 40.0 (#125)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 46.1% | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
Multilingual Not comparable
Qwen2.5 32B Instruct: —, Qwen3 32B: 45.6 (#167)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Not comparable
Qwen2.5 32B Instruct: —, Qwen3 32B: 68.9 (#179)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | — | 1305 |
Long Context Not comparable
Qwen2.5 32B Instruct: —, Qwen3 32B: 43.8 (#87)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |
Writing & Preference Not comparable
Qwen2.5 32B Instruct: —, Qwen3 32B: 52.9 (#163)
| Benchmark | Qwen2.5 32B Instruct | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |
Frequently asked questions
Is Qwen2.5 32B Instruct better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 30.1 on the Noometry Index.
Which is cheaper, Qwen2.5 32B Instruct or Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.
Is Qwen2.5 32B Instruct or Qwen3 32B better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Qwen2.5 32B Instruct and Qwen3 32B share?
4 benchmarks have published results for both models. Qwen2.5 32B Instruct has 7 scored results on Noometry and Qwen3 32B has 26.