Qwen3.5 122B A10B vs Qwen3.8 Max: Specs & Benchmark Comparison
Qwen3.5 122B A10B and Qwen3.8 Max both come from Alibaba, Qwen3.5 122B A10B was released in March 2026, and Qwen3.8 Max followed 5 months later in August 2026. Qwen3.8 Max is the larger model at roughly 2.4 trillion parameters, against 122 billion for Qwen3.5 122B A10B.
The two models share 12 published benchmarks. Qwen3.8 Max leads on 11 of them, Qwen3.5 122B A10B on 1. The widest gaps are on OSWorld-Verified, where Qwen3.8 Max scores 86.1% against 58.0%; WideSearch, where Qwen3.8 Max scores 81.9% against 60.5%. Averaged across everything we track, Qwen3.5 122B A10B sits at 70.9% and Qwen3.8 Max at 71.0%.
Qwen3.8 Max is available through an API at $2.50 per million input tokens with a 1M-token context window. We do not track a hosted API for Qwen3.5 122B A10B, so pricing and context cannot be compared directly.
| Characteristic | Qwen3.5 122B A10B | Qwen3.8 Max |
|---|---|---|
| Company | Alibaba | Alibaba |
| Release Date | March 1, 2026 | August 2, 2026 |
| Parameters | 122B | 2.4T |
| Multimodal | No | Yes |
| Context (input) | — | 1.0M |
| Context (output) | — | 131K |
| Input Price / 1M | — | $2.50 |
| Output Price / 1M | — | $6.25 |
| Average Score | 70.9% | 71.0% |
| Benchmarks | ||
| OSWorld-Verified | 58.0% | 86.1% |
| WideSearch | 60.5% | 81.9% |
| ERQA | 62.0% | 77.8% |
| ScreenSpot Pro | 70.4% | 84.5% |
| LVBench | 74.4% | 81.8% |
| IFBench | 76.1% | 82.8% |
| LongBench v2 | 60.2% | 66.3% |
| GPQA | 86.6% | 92.6% |
| MMMU-Pro | 76.9% | 82.3% |
| Humanity's Last Exam | 47.5% | 43.6% |
| VideoMME w sub. | 87.3% | 90.4% |
| RealWorldQA | 85.1% | 88.0% |
Visual Benchmark Comparison
Verdict
Qwen3.8 Max leads in 1 out of 2 comparison categories.
Both models show comparable average scores: Qwen3.5 122B A10B — 0.7, Qwen3.8 Max — 0.7.
Qwen3.8 Max is newer: released 8/2/2026 vs 3/1/2026.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — Qwen3.5 122B A10B or Qwen3.8 Max?
Which model is cheaper — Qwen3.5 122B A10B or Qwen3.8 Max?
Which has a larger context window — Qwen3.5 122B A10B or Qwen3.8 Max?
The Qwen3.5 122B A10B and Qwen3.8 Max comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Qwen3.5 122B A10B or Qwen3.8 Max page. See also the complete list of AI model comparisons.