Model comparison
DeepSeek-V3.2-Exp vs Qwen3-Coder 480B-A35B Instruct
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 38.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 8 categories and Qwen3-Coder 480B-A35B Instruct in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 37.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 70% for DeepSeek-V3.2-Exp and 55.4% for Qwen3-Coder 480B-A35B Instruct.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 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 164K.
Side by side
| DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 44.3 | 38.1 |
| Released | 2025-09-29 | 2025-04 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.26 | $1.50 |
| Output $ / M tokens | $0.38 | $7.50 |
| Results tracked | 49 | 25 |
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: 46.5 (#65), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 70% | 55.4% |
| LMArena WebDev | 1362 | 1275 |
| WeirdML | 39.5% | 41.2% |
| LMArena Coding | 1454 | 1412 |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| GSO | — | 4.9% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 32.7 (#59), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | 39.6% | 27.2% |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
DeepSeek-V3.2-Exp: 22.1 (#208), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 49.5% |
| LMArena Hard Prompts | 1434 | 1372 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.27 | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1435 | 1365 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1436 | 1338 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1409 | 1346 |
| LMArena Chinese | 1461 | 1357 |
| LMArena French | 1433 | 1398 |
| LMArena German | 1440 | 1325 |
| LMArena Japanese | 1374 | 1310 |
| LMArena Korean | 1371 | 1305 |
| LMArena Russian | 1424 | 1366 |
| LMArena Spanish | 1440 | 1360 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.5 (#93), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1413 | 1355 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1428 | 1378 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.4 (#77), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1425 | 1357 |
| LMArena Creative Writing | 1403 | 1333 |
| LMArena Multi-Turn | 1427 | 1365 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Qwen3-Coder 480B-A35B Instruct?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 38.1 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or Qwen3-Coder 480B-A35B Instruct?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is DeepSeek-V3.2-Exp or Qwen3-Coder 480B-A35B Instruct better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and Qwen3-Coder 480B-A35B Instruct share?
22 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.