Model comparison
GPT-5.2 vs Qwen3.5-122B-A10B
Head-to-head evidence from 18 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.2 #64 (Estimated); Qwen3.5-122B-A10B #47 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.2 and Qwen3.5-122B-A10B share 18 comparable benchmark results. 5 of 8 categories are comparable. 10 results are unique to GPT-5.2; 13 to Qwen3.5-122B-A10B.
Updated July 23, 2026- Shared results
- 18
- GPT-5.2 only
- 10
- Qwen3.5-122B-A10B only
- 13
- Comparable categories
- 5 / 8
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. GPT-5.2 only becomes the better choice if knowledge is the priority or you need the larger 400K context window.
Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 6 evidence categories; 5 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 has the cleaner BenchAlign overall profile here, landing at 60.56 versus 58.43. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Qwen3.5-122B-A10B's sharpest advantage is in reasoning, where it averages 60.2 against 52.9. The single biggest benchmark swing on the page is OSWorld-Verified, 47.3% to 58%. GPT-5.2 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GPT-5.2 is also the more expensive model on tokens at $1.75 input / $14.00 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. GPT-5.2 gives you the larger context window at 400K, 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 | GPT-5.2 | Δ | Qwen3.5-122B-A10B |
|---|---|---|---|
| Knowledge | GPT-5.292.4 | Margin← 8.8 | Qwen3.5-122B-A10B83.6 |
| Reasoning | GPT-5.252.9 | Margin→ 7.3 | Qwen3.5-122B-A10B60.2 |
| Multimodal | GPT-5.280.4 | Margin← 3.2 | Qwen3.5-122B-A10B77.2 |
| Coding | GPT-5.270.6 | Margin→ 1.4 | Qwen3.5-122B-A10B72.0 |
| Agentic | GPT-5.255.7 | Margin→ 0.7 | Qwen3.5-122B-A10B56.4 |
| Math | GPT-5.235.2 | MarginNo overlap | Qwen3.5-122B-A10BNot measured |
| Multilingual | GPT-5.2Not measured | MarginNo overlap | Qwen3.5-122B-A10B82.2 |
| Inst. Following | GPT-5.2Not 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 ↗
OSWorld-Verified
AgenticA 47.3%B 58%Winner: Qwen3.5-122B-A10BΔ 10.7OSWorld-Verified: GPT-5.2 scored 47.3%; Qwen3.5-122B-A10B scored 58%. Qwen3.5-122B-A10B wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 80%B 72%Winner: GPT-5.2Δ 8SWE-bench Verified: GPT-5.2 scored 80%; Qwen3.5-122B-A10B scored 72%. GPT-5.2 wins this benchmark. - Source ↗
GPQA
KnowledgeA 92.4%B 86.6%Winner: GPT-5.2Δ 5.8GPQA: GPT-5.2 scored 92.4%; Qwen3.5-122B-A10B scored 86.6%. GPT-5.2 wins this benchmark. - Source ↗
CharXiv
MultimodalA 82.1%B 77.2%Winner: GPT-5.2Δ 4.9CharXiv: GPT-5.2 scored 82.1%; Qwen3.5-122B-A10B scored 77.2%. GPT-5.2 wins this benchmark. - Source ↗
BrowseComp
AgenticA 65.8%B 63.8%Winner: GPT-5.2Δ 2BrowseComp: GPT-5.2 scored 65.8%; Qwen3.5-122B-A10B scored 63.8%. GPT-5.2 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.2 | Qwen3.5-122B-A10B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.2$1.75 input / $14 output | Qwen3.5-122B-A10B$0 input / $0 output | Qwen3.5-122B-A10B has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.273 tok/s | Qwen3.5-122B-A10BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.2130.34 s | Qwen3.5-122B-A10BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.2400K | Qwen3.5-122B-A10B262K | GPT-5.2 lists the larger context window. |
Benchmark Deep Dive
AgenticQwen3.5-122B-A10B wins9 benchmarks
| Benchmark | GPT-5.2 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| BrowseCompSource | 65.8% | 63.8% | GPT-5.2 leads |
| OSWorld-VerifiedSource | 47.3% | 58% | Qwen3.5-122B-A10B leads |
| τ²-bench resultsSource | 84.8% | 93.6% | Qwen3.5-122B-A10B leads |
| Gert LabsSource | 46.54% | — | Not comparable |
| JobBenchSource | 34.3% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 49.4% | Not comparable |
| AA Agentic IndexSource | — | 20.7% | Not comparable |
| GDPval-AASource | — | 23.9% | Not comparable |
| GDPval-AASource | — | 978 | Not comparable |
CodingQwen3.5-122B-A10B wins5 benchmarks
ReasoningQwen3.5-122B-A10B wins4 benchmarks
KnowledgeGPT-5.2 wins9 benchmarks
| Benchmark | GPT-5.2 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| GPQASource | 92.4% | 86.6% | GPT-5.2 leads |
| Artificial Analysis Intelligence IndexSource | 42.2% | 32.3% | GPT-5.2 leads |
| AA-GPQA DiamondSource | 90.3% | 85.7% | GPT-5.2 leads |
| AA-HLESource | 35.4% | 23.4% | GPT-5.2 leads |
| AA-Omniscience IndexSource | -1.0% | -39.6% | GPT-5.2 leads |
| AA-Omniscience AccuracySource | 43.8% | 24.7% | GPT-5.2 leads |
| AA-Omniscience Hallucination RateSource | 79.7% | 85.5% | GPT-5.2 leads |
| MMLU-ProSource | — | 86.7% | Not comparable |
| SuperGPQASource | — | 67.1% | Not comparable |
Math3 benchmarks
Multilingual1 benchmarks
| Benchmark | GPT-5.2 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| MMLU-ProXSource | — | 82.2% | Not comparable |
MultimodalGPT-5.2 wins8 benchmarks
| Benchmark | GPT-5.2 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| MMMU-ProSource | 79.5% | — | Not comparable |
| MathVisionSource | 83.0% | 86.2% | Qwen3.5-122B-A10B leads |
| CharXivSource | 82.1% | 77.2% | GPT-5.2 leads |
| V*Source | 75.9% | 93.2% | Qwen3.5-122B-A10B leads |
| Design Arena WebsiteSource | 1224 | — | Not comparable |
| MMMUSource | — | 83.9% | Not comparable |
| MMVUSource | — | 74.7% | Not comparable |
| AA-MMMU-ProSource | — | 75.0% | Not comparable |
Frequently Asked Questions (6)
Which is better, GPT-5.2 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B is ahead on BenchLM's BenchAlign leaderboard, 60.56 to 58.43. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 47.3% and 58%.
Which is better for knowledge tasks, GPT-5.2 or Qwen3.5-122B-A10B?
GPT-5.2 has the edge for knowledge tasks in this comparison, averaging 92.4 versus 83.6. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Which is better for coding, GPT-5.2 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 72 versus 70.6. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Which is better for reasoning, GPT-5.2 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for reasoning in this comparison, averaging 60.2 versus 52.9. Inside this category, CritPt is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.2 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for agentic tasks in this comparison, averaging 56.4 versus 55.7. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, GPT-5.2 or Qwen3.5-122B-A10B?
GPT-5.2 has the edge for multimodal and grounded tasks in this comparison, averaging 80.4 versus 77.2. Inside this category, V* 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.