Compare / head-to-head
DeepSeek V3.2-Expvs
Qwen3-Coder 30B-A3B Instruct
DeepSeek V3.2-Exp leads 2 of 2 shared benchmarks. Qwen3-Coder 30B-A3B Instruct has the larger context window (262K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
DeepSeek V3.2-Exp leads
Cheaper per token
—
list price, input + output
Larger context
Qwen3-Coder 30B-A3B Instruct
262K tokens
Providers
2 providers
DeepSeek · Qwen
DeepSeek V3.2-Exp
DeepSeek · released 2025-09-29
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 17 · 7 core
Qwen3-Coder 30B-A3B Instruct
Qwen · released 2025-07-31
text
Quality
Benchmark matrix
2 shared · 15 only DeepSeek V3.2-Exp · 11 only Qwen3-Coder 30B-A3B Instruct| Benchmark | DeepSeek V3.2-Exp | Qwen3-Coder 30B-A3B Instruct | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| Aider-Polyglot | 74.5% ↗ | 33.3% ↗ | +41.2 pt | DeepSeek V3.2-Exp |
| SWE-bench Multilingual | 57.9% ↗ | 34.7% ↗ | +23.2 pt | DeepSeek V3.2-Exp |
| Only DeepSeek V3.2-Exp reports · 15 | ||||
| MMLU-Pro | 85% ↗ | not reported | — | — |
| AIME 2025 | 89.3% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 19.8% ↗ | not reported | — | — |
| LMArena Elo | 1424.9 ↗ | not reported | — | — |
| BrowseComp | 40.1% ↗ | not reported | — | — |
| BrowseComp-zh | 47.9% ↗ | not reported | — | — |
| GPQA-Diamond | 79.9% ↗ | not reported | — | — |
| HMMT 2025 | 83.6% ↗ | not reported | — | — |
| LiveCodeBench | 74.1% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1271.8 ↗ | not reported | — | — |
| SimpleQA (agentic tool use) | 97.1% ↗ | not reported | — | — |
| SWE Verified | 67.8% ↗ | not reported | — | — |
| Terminal-bench | 37.7% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 1034 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 39.5% ↗ | not reported | — | — |
| Only Qwen3-Coder 30B-A3B Instruct reports · 11 | ||||
| BFCL-v3 | not reported | 62.2% ↗ | — | — |
| Mind2Web | not reported | 51% ↗ | — | — |
| Multi-SWE-bench flash | not reported | 19.3% ↗ | — | — |
| Multi-SWE-bench mini | not reported | 19.5% ↗ | — | — |
| Spider2 | not reported | 21.4% ↗ | — | — |
| SWE-bench Live | not reported | 20.7% ↗ | — | — |
| SWE-bench Verified (w/ OpenHands, 500 turns) | not reported | 51.6% ↗ | — | — |
| TAU-Bench Airline | not reported | 48% ↗ | — | — |
| TAU-Bench Retail | not reported | 68.7% ↗ | — | — |
| Terminal-Bench | not reported | 31.3% ↗ | — | — |
| WebArena | not reported | 43.5% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek V3.2-Exp minus Qwen3-Coder 30B-A3B Instruct in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | DeepSeek V3.2-Exp | Qwen3-Coder 30B-A3B Instruct | Edge |
|---|---|---|---|
| Context window | 128K tokens | 262K tokens | Qwen3-Coder 30B-A3B Instruct |
| Max output | — | — | — |
| Input price / 1M | — | $0.45 ↗ | — |
| Output price / 1M | — | $2.25 ↗ | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $2.7 | — |
| Modalities | text | text | Tie |
| Released | 2025-09-29 | 2025-07-31 | — |
| Cited benchmark scores | 17 | 13 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V3.2-Exp vs …
Models sharing the most benchmarksMore matchups
Qwen3-Coder 30B-A3B Instruct vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3.2-Exp and Qwen3-Coder 30B-A3B Instruct on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.