Model comparison
DeepSeek V4 Pro vs Qwen3.6-35B-A3B
Head-to-head evidence from 13 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: DeepSeek V4 Pro #46 (Supported); Qwen3.6-35B-A3B #104 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. DeepSeek V4 Pro and Qwen3.6-35B-A3B share 13 comparable benchmark results. 4 of 8 categories are comparable. 10 results are unique to DeepSeek V4 Pro; 44 to Qwen3.6-35B-A3B.
Updated July 23, 2026- Shared results
- 13
- DeepSeek V4 Pro only
- 10
- Qwen3.6-35B-A3B only
- 44
- Comparable categories
- 4 / 8
Pick DeepSeek V4 Pro if you want the stronger benchmark profile. Qwen3.6-35B-A3B only becomes the better choice if mathematics is the priority or you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 13 shared benchmark results across 4 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
DeepSeek V4 Pro is clearly ahead on the BenchAlign aggregate, 60.66 to 51.47. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek V4 Pro's sharpest advantage is in agentic, where it averages 59.1 against 51.5. The single biggest benchmark swing on the page is HMMT Feb 2026, 31.7% to 83.6%. Qwen3.6-35B-A3B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.
Qwen3.6-35B-A3B is the reasoning model in the pair, while DeepSeek V4 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. DeepSeek V4 Pro gives you the larger context window at 1M, compared with 262K for Qwen3.6-35B-A3B.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | DeepSeek V4 Pro | Δ | Qwen3.6-35B-A3B |
|---|---|---|---|
| Math | DeepSeek V4 Pro31.7 | Margin→ 56.5 | Qwen3.6-35B-A3B88.2 |
| Knowledge | DeepSeek V4 Pro41.3 | Margin→ 10.1 | Qwen3.6-35B-A3B51.4 |
| Coding | DeepSeek V4 Pro65.3 | Margin→ 8.5 | Qwen3.6-35B-A3B73.8 |
| Agentic | DeepSeek V4 Pro59.1 | Margin← 7.6 | Qwen3.6-35B-A3B51.5 |
| Multimodal | DeepSeek V4 ProNot measured | MarginNo overlap | Qwen3.6-35B-A3B76.3 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
HMMT Feb 2026
MathA 31.7%B 83.6%Winner: Qwen3.6-35B-A3BΔ 51.9HMMT Feb 2026: DeepSeek V4 Pro scored 31.7%; Qwen3.6-35B-A3B scored 83.6%. Qwen3.6-35B-A3B wins this benchmark. - Source ↗
HLE
KnowledgeA 7.7%B 21.4%Winner: Qwen3.6-35B-A3BΔ 13.7HLE: DeepSeek V4 Pro scored 7.7%; Qwen3.6-35B-A3B scored 21.4%. Qwen3.6-35B-A3B wins this benchmark. - Source ↗
GPQA
KnowledgeA 72.9%B 86%Winner: Qwen3.6-35B-A3BΔ 13.1GPQA: DeepSeek V4 Pro scored 72.9%; Qwen3.6-35B-A3B scored 86%. Qwen3.6-35B-A3B wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 59.1%B 51.5%Winner: DeepSeek V4 ProΔ 7.6Terminal-Bench 2.0: DeepSeek V4 Pro scored 59.1%; Qwen3.6-35B-A3B scored 51.5%. DeepSeek V4 Pro wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 52.1%B 49.5%Winner: DeepSeek V4 ProΔ 2.6SWE-bench Pro: DeepSeek V4 Pro scored 52.1%; Qwen3.6-35B-A3B scored 49.5%. DeepSeek V4 Pro wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | DeepSeek V4 Pro | Qwen3.6-35B-A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | DeepSeek V4 Pro$0.435 input / $0.87 output | Qwen3.6-35B-A3BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | DeepSeek V4 ProNot available | Qwen3.6-35B-A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | DeepSeek V4 ProNot available | Qwen3.6-35B-A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | DeepSeek V4 Pro1M | Qwen3.6-35B-A3B262K | DeepSeek V4 Pro lists the larger context window. |
Benchmark Deep Dive
AgenticDeepSeek V4 Pro wins16 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 59.1% | 51.5% | DeepSeek V4 Pro leads |
| MCP AtlasSource | 69.4% | 62.8% | DeepSeek V4 Pro leads |
| ToolathlonSource | 46.3% | 26.9% | DeepSeek V4 Pro leads |
| Claw-EvalSource | 59.8% | 68.7% | Qwen3.6-35B-A3B leads |
| Gert LabsSource | 50.28% | 42.65% | DeepSeek V4 Pro leads |
| ResearchClawBenchSource | 17.1% | — | Not comparable |
| QwenClawBenchSource | — | 52.6% | Not comparable |
| QwenWebBenchSource | — | 1397 | Not comparable |
| τ³-bench resultsSource | — | 67.2% | Not comparable |
| VITA-BenchSource | — | 35.6% | Not comparable |
| DeepPlanningSource | — | 25.9% | Not comparable |
| WideResearchSource | — | 60.1% | Not comparable |
| AA Agentic IndexSource | — | 21.4% | Not comparable |
| τ²-bench resultsSource | — | 95.3% | Not comparable |
| GDPval-AASource | — | 27.4% | Not comparable |
| GDPval-AASource | — | 1049 | Not comparable |
CodingQwen3.6-35B-A3B wins8 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 73.6% | 73.4% | DeepSeek V4 Pro leads |
| SWE-bench ProSource | 52.1% | 49.5% | DeepSeek V4 Pro leads |
| SWE MultilingualSource | 69.8% | 67.2% | DeepSeek V4 Pro leads |
| Terminal-Bench 2.0Source | 59.1% | 51.5% | DeepSeek V4 Pro leads |
| LiveCodeBenchSource | — | 80.4% | Not comparable |
| NL2RepoSource | — | 29.4% | Not comparable |
| AA Coding IndexSource | — | 41.9% | Not comparable |
| AA-SciCodeSource | — | 35.8% | Not comparable |
Reasoning4 benchmarks
KnowledgeQwen3.6-35B-A3B wins14 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| MMLU-ProSource | 82.9% | 85.2% | Qwen3.6-35B-A3B leads |
| SimpleQASource | 45% | — | Not comparable |
| Chinese-SimpleQASource | 75.8% | — | Not comparable |
| GPQASource | 72.9% | 86% | Qwen3.6-35B-A3B leads |
| GPQA-DSource | 72.9% | — | Not comparable |
| HLESource | 7.7% | 21.4% | Qwen3.6-35B-A3B leads |
| SuperGPQASource | — | 64.7% | Not comparable |
| C-EvalSource | — | 90% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 31.6% | Not comparable |
| AA-GPQA DiamondSource | — | 84.1% | Not comparable |
| AA-HLESource | — | 20.2% | Not comparable |
| AA-Omniscience IndexSource | — | -21.4% | Not comparable |
| AA-Omniscience AccuracySource | — | 18.9% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 49.7% | Not comparable |
MathQwen3.6-35B-A3B wins8 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| HMMT Feb 2026Source | 31.7% | 83.6% | Qwen3.6-35B-A3B leads |
| IMOAnswerBenchSource | 35.3% | — | Not comparable |
| ApexSource | 0.4% | — | Not comparable |
| Apex ShortlistSource | 9.2% | — | Not comparable |
| HMMT Feb 2025Source | — | 90.7% | Not comparable |
| HMMT Nov 2025Source | — | 89.1% | Not comparable |
| MMAnswerBenchSource | — | 78.9% | Not comparable |
| AIME26Source | — | 92.7% | Not comparable |
Multimodal16 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1264 | — | Not comparable |
| MMMUSource | — | 81.7% | Not comparable |
| MMMU-ProSource | — | 75.3% | Not comparable |
| RealWorldQASource | — | 85.3% | Not comparable |
| OmniDocBench 1.5Source | — | 89.9% | Not comparable |
| CharXivSource | — | 78% | Not comparable |
| SimpleVQASource | — | 58.9% | Not comparable |
| CC-OCRSource | — | 81.9% | Not comparable |
| AI2D_TESTSource | — | 92.7% | Not comparable |
| RefCOCO (avg)Source | — | 92.0% | Not comparable |
| ODINW13Source | — | 50.8% | Not comparable |
| Video-MME (with subtitle)Source | — | 86.6% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 82.5% | Not comparable |
| VideoMMMUSource | — | 83.7% | Not comparable |
| MLVU (M-Avg)Source | — | 86.2% | Not comparable |
| AA-MMMU-ProSource | — | 75.0% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 64.4% | Not comparable |
Frequently Asked Questions (5)
Which is better, DeepSeek V4 Pro or Qwen3.6-35B-A3B?
DeepSeek V4 Pro is ahead on BenchLM's BenchAlign leaderboard, 60.66 to 51.47. The biggest single separator in this matchup is HMMT Feb 2026, where the scores are 31.7% and 83.6%.
Which is better for knowledge tasks, DeepSeek V4 Pro or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for knowledge tasks in this comparison, averaging 51.4 versus 41.3. Inside this category, HLE is the benchmark that creates the most daylight between them.
Which is better for coding, DeepSeek V4 Pro or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 65.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for math, DeepSeek V4 Pro or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for math in this comparison, averaging 88.2 versus 31.7. Inside this category, HMMT Feb 2026 is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, DeepSeek V4 Pro or Qwen3.6-35B-A3B?
DeepSeek V4 Pro has the edge for agentic tasks in this comparison, averaging 59.1 versus 51.5. Inside this category, Toolathlon is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.