Model comparison
DeepSeek V4 Pro vs Qwen3.5-122B-A10B
Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: DeepSeek V4 Pro #46 (Supported); Qwen3.5-122B-A10B #47 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. DeepSeek V4 Pro and Qwen3.5-122B-A10B share 4 comparable benchmark results. 3 of 8 categories are comparable. 19 results are unique to DeepSeek V4 Pro; 27 to Qwen3.5-122B-A10B.
Updated July 23, 2026- Shared results
- 4
- DeepSeek V4 Pro only
- 19
- Qwen3.5-122B-A10B only
- 27
- Comparable categories
- 3 / 8
Pick DeepSeek V4 Pro if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 3 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 has the cleaner BenchAlign overall profile here, landing at 60.66 versus 60.56. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
DeepSeek V4 Pro's sharpest advantage is in agentic, where it averages 59.1 against 56.4. The single biggest benchmark swing on the page is GPQA, 72.9% to 86.6%. Qwen3.5-122B-A10B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
DeepSeek V4 Pro is also the more expensive model on tokens at $0.43 input / $0.87 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-122B-A10B. That is roughly Infinityx on output cost alone. Qwen3.5-122B-A10B 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 Qwen3.5-122B-A10B.
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 | Qwen3.5-122B-A10B |
|---|---|---|---|
| Knowledge | DeepSeek V4 Pro41.3 | Margin→ 42.3 | Qwen3.5-122B-A10B83.6 |
| Coding | DeepSeek V4 Pro65.3 | Margin→ 6.7 | Qwen3.5-122B-A10B72.0 |
| Agentic | DeepSeek V4 Pro59.1 | Margin← 2.7 | Qwen3.5-122B-A10B56.4 |
| Reasoning | DeepSeek V4 ProNot measured | MarginNo overlap | Qwen3.5-122B-A10B60.2 |
| Math | DeepSeek V4 Pro31.7 | MarginNo overlap | Qwen3.5-122B-A10BNot measured |
| Multilingual | DeepSeek V4 ProNot measured | MarginNo overlap | Qwen3.5-122B-A10B82.2 |
| Multimodal | DeepSeek V4 ProNot measured | MarginNo overlap | Qwen3.5-122B-A10B77.2 |
| Inst. Following | DeepSeek V4 ProNot measured | MarginNo overlap | Qwen3.5-122B-A10B93.4 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
GPQA
KnowledgeA 72.9%B 86.6%Winner: Qwen3.5-122B-A10BΔ 13.7GPQA: DeepSeek V4 Pro scored 72.9%; Qwen3.5-122B-A10B scored 86.6%. Qwen3.5-122B-A10B wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 59.1%B 49.4%Winner: DeepSeek V4 ProΔ 9.7Terminal-Bench 2.0: DeepSeek V4 Pro scored 59.1%; Qwen3.5-122B-A10B scored 49.4%. DeepSeek V4 Pro wins this benchmark. - Source ↗
MMLU-Pro
KnowledgeA 82.9%B 86.7%Winner: Qwen3.5-122B-A10BΔ 3.8MMLU-Pro: DeepSeek V4 Pro scored 82.9%; Qwen3.5-122B-A10B scored 86.7%. Qwen3.5-122B-A10B wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 73.6%B 72%Winner: DeepSeek V4 ProΔ 1.6SWE-bench Verified: DeepSeek V4 Pro scored 73.6%; Qwen3.5-122B-A10B scored 72%. 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 | Qwen3.5-122B-A10B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | DeepSeek V4 Pro$0.435 input / $0.87 output | Qwen3.5-122B-A10B$0 input / $0 output | Qwen3.5-122B-A10B has the lower combined listed price. |
| Generation speedtokens per second | DeepSeek V4 ProNot available | Qwen3.5-122B-A10BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | DeepSeek V4 ProNot available | Qwen3.5-122B-A10BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | DeepSeek V4 Pro1M | Qwen3.5-122B-A10B262K | DeepSeek V4 Pro lists the larger context window. |
Benchmark Deep Dive
AgenticDeepSeek V4 Pro wins12 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 59.1% | 49.4% | DeepSeek V4 Pro leads |
| MCP AtlasSource | 69.4% | — | Not comparable |
| ToolathlonSource | 46.3% | — | Not comparable |
| Claw-EvalSource | 59.8% | — | Not comparable |
| Gert LabsSource | 50.28% | — | Not comparable |
| ResearchClawBenchSource | 17.1% | — | Not comparable |
| BrowseCompSource | — | 63.8% | Not comparable |
| OSWorld-VerifiedSource | — | 58% | Not comparable |
| τ²-bench resultsSource | — | 93.6% | Not comparable |
| AA Agentic IndexSource | — | 20.7% | Not comparable |
| GDPval-AASource | — | 23.9% | Not comparable |
| GDPval-AASource | — | 978 | Not comparable |
CodingQwen3.5-122B-A10B wins6 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 73.6% | 72% | DeepSeek V4 Pro leads |
| SWE-bench ProSource | 52.1% | — | Not comparable |
| SWE MultilingualSource | 69.8% | — | Not comparable |
| Terminal-Bench 2.0Source | 59.1% | — | Not comparable |
| AA Coding IndexSource | — | 45.7% | Not comparable |
| AA-SciCodeSource | — | 42.0% | Not comparable |
Reasoning5 benchmarks
KnowledgeQwen3.5-122B-A10B wins13 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| MMLU-ProSource | 82.9% | 86.7% | Qwen3.5-122B-A10B leads |
| SimpleQASource | 45% | — | Not comparable |
| Chinese-SimpleQASource | 75.8% | — | Not comparable |
| GPQASource | 72.9% | 86.6% | Qwen3.5-122B-A10B leads |
| GPQA-DSource | 72.9% | — | Not comparable |
| HLESource | 7.7% | — | Not comparable |
| SuperGPQASource | — | 67.1% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 32.3% | Not comparable |
| AA-GPQA DiamondSource | — | 85.7% | Not comparable |
| AA-HLESource | — | 23.4% | Not comparable |
| AA-Omniscience IndexSource | — | -39.6% | Not comparable |
| AA-Omniscience AccuracySource | — | 24.7% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 85.5% | Not comparable |
Math4 benchmarks
Multilingual1 benchmarks
| Benchmark | DeepSeek V4 Pro | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| MMLU-ProXSource | — | 82.2% | Not comparable |
Multimodal7 benchmarks
Frequently Asked Questions (4)
Which is better, DeepSeek V4 Pro or Qwen3.5-122B-A10B?
DeepSeek V4 Pro is ahead on BenchLM's BenchAlign leaderboard, 60.66 to 60.56. The biggest single separator in this matchup is GPQA, where the scores are 72.9% and 86.6%.
Which is better for knowledge tasks, DeepSeek V4 Pro or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 83.6 versus 41.3. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Which is better for coding, DeepSeek V4 Pro or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 72 versus 65.3. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, DeepSeek V4 Pro or Qwen3.5-122B-A10B?
DeepSeek V4 Pro has the edge for agentic tasks in this comparison, averaging 59.1 versus 56.4. Inside this category, Terminal-Bench 2.0 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.