Model comparison
Qwen3.5-122B-A10B vs Qwen3.6-27B
Head-to-head evidence from 24 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Qwen3.5-122B-A10B #47 (Supported); Qwen3.6-27B #93 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Qwen3.5-122B-A10B and Qwen3.6-27B share 24 comparable benchmark results. 4 of 8 categories are comparable. 7 results are unique to Qwen3.5-122B-A10B; 30 to Qwen3.6-27B.
Updated July 21, 2026- Shared results
- 24
- Qwen3.5-122B-A10B only
- 7
- Qwen3.6-27B only
- 30
- Comparable categories
- 4 / 8
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. Qwen3.6-27B only becomes the better choice if coding is the priority.
Confidence note. This is a partial-evidence comparison with 24 shared benchmark results across 6 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
Qwen3.5-122B-A10B is clearly ahead on the BenchAlign aggregate, 60.56 to 53.82. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.5-122B-A10B's sharpest advantage is in knowledge, where it averages 83.6 against 53.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 49.4% to 59.3%. Qwen3.6-27B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
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 | Qwen3.5-122B-A10B | Δ | Qwen3.6-27B |
|---|---|---|---|
| Knowledge | Qwen3.5-122B-A10B83.6 | Margin← 30.3 | Qwen3.6-27B53.3 |
| Coding | Qwen3.5-122B-A10B72.0 | Margin→ 5.5 | Qwen3.6-27B77.5 |
| Agentic | Qwen3.5-122B-A10B56.4 | Margin→ 2.9 | Qwen3.6-27B59.3 |
| Multimodal | Qwen3.5-122B-A10B77.2 | Margin← 0.5 | Qwen3.6-27B76.7 |
| Reasoning | Qwen3.5-122B-A10B60.2 | MarginNo overlap | Qwen3.6-27BNot measured |
| Math | Qwen3.5-122B-A10BNot measured | MarginNo overlap | Qwen3.6-27B89.2 |
| Multilingual | Qwen3.5-122B-A10B82.2 | MarginNo overlap | Qwen3.6-27BNot measured |
| Inst. Following | Qwen3.5-122B-A10B93.4 | MarginNo overlap | Qwen3.6-27BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 49.4%B 59.3%Winner: Qwen3.6-27BΔ 9.9Terminal-Bench 2.0: Qwen3.5-122B-A10B scored 49.4%; Qwen3.6-27B scored 59.3%. Qwen3.6-27B wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 72%B 77.2%Winner: Qwen3.6-27BΔ 5.2SWE-bench Verified: Qwen3.5-122B-A10B scored 72%; Qwen3.6-27B scored 77.2%. Qwen3.6-27B wins this benchmark. - Source ↗
GPQA
KnowledgeA 86.6%B 87.8%Winner: Qwen3.6-27BΔ 1.2GPQA: Qwen3.5-122B-A10B scored 86.6%; Qwen3.6-27B scored 87.8%. Qwen3.6-27B wins this benchmark. - Source ↗
CharXiv
MultimodalA 77.2%B 78.4%Winner: Qwen3.6-27BΔ 1.2CharXiv: Qwen3.5-122B-A10B scored 77.2%; Qwen3.6-27B scored 78.4%. Qwen3.6-27B wins this benchmark. - Source ↗
SuperGPQA
KnowledgeA 67.1%B 66%Winner: Qwen3.5-122B-A10BΔ 1.1SuperGPQA: Qwen3.5-122B-A10B scored 67.1%; Qwen3.6-27B scored 66%. Qwen3.5-122B-A10B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Qwen3.5-122B-A10B | Qwen3.6-27B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Qwen3.5-122B-A10B$0 input / $0 output | Qwen3.6-27B$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | Qwen3.5-122B-A10BNot available | Qwen3.6-27BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Qwen3.5-122B-A10BNot available | Qwen3.6-27BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Qwen3.5-122B-A10B262K | Qwen3.6-27B262K | Listed context windows are equal. |
Benchmark Deep Dive
AgenticQwen3.6-27B wins12 benchmarks
| Benchmark | Qwen3.5-122B-A10B | Qwen3.6-27B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 49.4% | 59.3% | Qwen3.6-27B leads |
| BrowseCompSource | 63.8% | — | Not comparable |
| OSWorld-VerifiedSource | 58% | — | Not comparable |
| τ²-bench resultsSource | 93.6% | 94.2% | Qwen3.6-27B leads |
| AA Agentic IndexSource | 20.7% | 27.0% | Qwen3.6-27B leads |
| GDPval-AASource | 23.9% | 32.0% | Qwen3.6-27B leads |
| GDPval-AASource | 978 | 1140 | Qwen3.6-27B leads |
| Claw-EvalSource | — | 72.4% | Not comparable |
| QwenClawBenchSource | — | 53.4% | Not comparable |
| QwenWebBenchSource | — | 1487 | Not comparable |
| AndroidWorldSource | — | 70.3% | Not comparable |
| Gert LabsSource | — | 54.84% | Not comparable |
CodingQwen3.6-27B wins8 benchmarks
| Benchmark | Qwen3.5-122B-A10B | Qwen3.6-27B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 72% | 77.2% | Qwen3.6-27B leads |
| AA Coding IndexSource | 45.7% | 53.7% | Qwen3.6-27B leads |
| AA-SciCodeSource | 42.0% | 39.8% | Qwen3.5-122B-A10B leads |
| SWE MultilingualSource | — | 71.3% | Not comparable |
| SWE-bench ProSource | — | 53.5% | Not comparable |
| Terminal-Bench 2.0Source | — | 59.3% | Not comparable |
| LiveCodeBenchSource | — | 83.9% | Not comparable |
| NL2RepoSource | — | 36.2% | Not comparable |
Reasoning3 benchmarks
KnowledgeQwen3.5-122B-A10B wins12 benchmarks
| Benchmark | Qwen3.5-122B-A10B | Qwen3.6-27B | Result |
|---|---|---|---|
| MMLU-ProSource | 86.7% | 86.2% | Qwen3.5-122B-A10B leads |
| SuperGPQASource | 67.1% | 66% | Qwen3.5-122B-A10B leads |
| GPQASource | 86.6% | 87.8% | Qwen3.6-27B leads |
| Artificial Analysis Intelligence IndexSource | 32.3% | 37.0% | Qwen3.6-27B leads |
| AA-GPQA DiamondSource | 85.7% | 84.2% | Qwen3.5-122B-A10B leads |
| AA-HLESource | 23.4% | 21.6% | Qwen3.5-122B-A10B leads |
| AA-Omniscience IndexSource | -39.6% | -19.8% | Qwen3.6-27B leads |
| AA-Omniscience AccuracySource | 24.7% | 19.2% | Qwen3.5-122B-A10B leads |
| AA-Omniscience Hallucination RateSource | 85.5% | 48.3% | Qwen3.6-27B leads |
| MMLU-ReduxSource | — | 93.5% | Not comparable |
| C-EvalSource | — | 91.4% | Not comparable |
| HLESource | — | 24% | Not comparable |
Math5 benchmarks
Multilingual1 benchmarks
| Benchmark | Qwen3.5-122B-A10B | Qwen3.6-27B | Result |
|---|---|---|---|
| MMLU-ProXSource | 82.2% | — | Not comparable |
MultimodalQwen3.5-122B-A10B wins18 benchmarks
| Benchmark | Qwen3.5-122B-A10B | Qwen3.6-27B | Result |
|---|---|---|---|
| MMMUSource | 83.9% | 82.9% | Qwen3.5-122B-A10B leads |
| MMVUSource | 74.7% | — | Not comparable |
| MathVisionSource | 86.2% | — | Not comparable |
| CharXivSource | 77.2% | 78.4% | Qwen3.6-27B leads |
| V*Source | 93.2% | 94.7% | Qwen3.6-27B leads |
| AA-MMMU-ProSource | 75.0% | 74.6% | Qwen3.5-122B-A10B leads |
| MMMU-ProSource | — | 75.8% | Not comparable |
| RealWorldQASource | — | 84.1% | Not comparable |
| DynaMathSource | — | 85.6% | Not comparable |
| MStarSource | — | 81.4% | Not comparable |
| SimpleVQASource | — | 56.1% | Not comparable |
| CC-OCRSource | — | 81.2% | Not comparable |
| CountBenchSource | — | 97.8% | Not comparable |
| RefCOCO (avg)Source | — | 92.5% | Not comparable |
| ERQASource | — | 62.5% | Not comparable |
| Video-MME (with subtitle)Source | — | 87.7% | Not comparable |
| VideoMMMUSource | — | 84.4% | Not comparable |
| MLVU (M-Avg)Source | — | 86.6% | Not comparable |
Frequently Asked Questions (5)
Which is better, Qwen3.5-122B-A10B or Qwen3.6-27B?
Qwen3.5-122B-A10B is ahead on BenchLM's BenchAlign leaderboard, 60.56 to 53.82. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 49.4% and 59.3%.
Which is better for knowledge tasks, Qwen3.5-122B-A10B or Qwen3.6-27B?
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 83.6 versus 53.3. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for coding, Qwen3.5-122B-A10B or Qwen3.6-27B?
Qwen3.6-27B has the edge for coding in this comparison, averaging 77.5 versus 72. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Qwen3.5-122B-A10B or Qwen3.6-27B?
Qwen3.6-27B has the edge for agentic tasks in this comparison, averaging 59.3 versus 56.4. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Qwen3.5-122B-A10B or Qwen3.6-27B?
Qwen3.5-122B-A10B has the edge for multimodal and grounded tasks in this comparison, averaging 77.2 versus 76.7. Inside this category, V* is the benchmark that creates the most daylight between them.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
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.