Model comparison
DeepSeek-V3.2-Exp vs Qwen2.5-Coder-32B
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 32.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.2-Exp leads 46.4 to 22.4.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 70% for DeepSeek-V3.2-Exp and 9% for Qwen2.5-Coder-32B.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 33K.
Side by side
| DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 44.9 | 32.9 |
| Released | 2025-09-29 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 164K | 33K |
| Max output | 66K | 29K |
| Input $ / M tokens | $0.26 | $0.66 |
| Output $ / M tokens | $0.38 | $1 |
| Results tracked | 48 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.4 (#61), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 70% | 9% |
| Aider Polyglot | 74.2% | 16.4% |
| LMArena Coding | 1454 | 1276 |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 37.9 (#31), Qwen2.5-Coder-32B: —
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.0 (#185), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1251 |
| Epoch Capabilities Index | 146.28 | 119.41 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| LiveBench Reasoning | — | 42.1% |
| DTBench | 87.7% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 29.1% | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 40.8 (#75), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1435 | 1251 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| LiveBench Math | — | 46.6% |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 93% |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.6 (#61), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1436 | 1221 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.4 (#85), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1409 | 1205 |
| LMArena Chinese | 1461 | 1222 |
| LMArena Russian | 1423 | 1228 |
| LMArena French | 1435 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1377 | — |
| LMArena Korean | 1372 | — |
| LMArena Spanish | 1441 | — |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.7 (#89), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1413 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1428 | 1251 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | DeepSeek-V3.2-Exp | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1425 | 1230 |
| LMArena Creative Writing | 1403 | 1174 |
| LMArena Multi-Turn | 1427 | 1222 |
| EQ-Bench Creative Writing | 1515 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Qwen2.5-Coder-32B?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 32.9 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or Qwen2.5-Coder-32B?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is DeepSeek-V3.2-Exp or Qwen2.5-Coder-32B better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 22.4 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.2-Exp does, with 164K tokens against 33K.
How many benchmarks do DeepSeek-V3.2-Exp and Qwen2.5-Coder-32B share?
15 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Qwen2.5-Coder-32B has 31.