← All benchmarks
Qwen3.5 122B A10B (Reasoning)
Alibaba · Released 2026-02-24 · Independent benchmark scores from Artificial Analysis
Intelligence Index
15.6
Output speed
133.7
tokens/sec
Blended price
$1.10
per 1M tokens
Time to first token
0.98s
Model metadata
| Model ID | 2236df45-0699-40d1-b5cc-69ee345d2257 |
|---|---|
| Slug | qwen3-5-122b-a10b |
| Release date | 2026-02-24 |
| Provider | Alibaba |
| Provider slug | alibaba |
| Output speed | 133.7 tok/s |
| Time to first token | 0.98s |
| Time to first answer | 15.94s |
| Blended price ($/1M) | $1.10 |
| Input price ($/1M) | $0.40 |
| Output price ($/1M) | $3.20 |
All evaluation scores (18)
| aime | — |
|---|---|
| aime 25 | — |
| artificial analysis coding index | 45.70 |
| artificial analysis intelligence index | 15.60 |
| artificial analysis math index | — |
| gpqa | 85.7% |
| hle | 25.2% |
| ifbench | 75.7% |
| lcr | 76.3% |
| livecodebench | — |
| math 500 | — |
| mmlu pro | — |
| scicode | 39.7% |
| tau banking | 15.3% |
| tau2 | 93.6% |
| terminalbench hard | 31.1% |
| terminalbench v2 1 | 47.6% |
| terminalbench v4 0 | 0.0% |
Source: artificialanalysis.ai/models/qwen3-5-122b-a10b
Benchmark data from Artificial Analysis.