Qwen3.5 397B A17B (Reasoning)
By Alibaba · released 2026-02-16 (8 months) · snapshot 2026-10-24
- Intelligence index
- 18.40
- Cost to run the AA index
- $941
- Price per 1M tokens (in / out)
- $0.60 / $3.60
- End-to-end time
- 64.8s
Is Qwen3.5 397B A17B (Reasoning) on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-6.1 Sol (Xhigh) is at least as smart for the same money or less.
Next step up: GPT-6.1 Sol (Max), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Qwen3.5 397B A17B (Reasoning) | Alibaba | 18.40 | $941 | 64.8s | 2026-02-16 | ||
| 2 | GPT-6.1 Sol (Xhigh) | OpenAI | 51.00 | $662 | 86.3s | 2026-09-29 | Frontier | |
| 3 | GPT-6.1 Sol (Max) | OpenAI | 51.80 | $1082 | 220.5s | 2026-09-29 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
Qwen3.5 397B A17B (Reasoning) today
1 of 2 effort levels plotted. The remaining levels lack intelligence or benchmark cost data.
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: qwen3-5-397b-a17b.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- Qwen3.5 397B A17B (Reasoning) vs GPT-6.1 Sol (Xhigh)
- Qwen3.5 397B A17B (Reasoning) vs GPT-6.1 Sol (Max)
- Qwen3.5 397B A17B (Reasoning) vs Qwen3.5 397B A17B (Non-reasoning)
- Qwen3.5 397B A17B (Reasoning) vs GPT-6.1 Sol (Medium)
- Qwen3.5 397B A17B (Reasoning) vs GPT-6.1 Sol (High)
- Qwen3.5 397B A17B (Reasoning) vs Claude Opus 5.5 (High, Default Fallback)
What the Qwen3.5 397B A17B release did to the frontier on 2026-02-16
1 of 2 effort levels reached the frontier at launch (Qwen3.5 397B A17B (Reasoning)). Impact 0.30, #32 of 46 releases this past year.
Should you use Qwen3.5 397B A17B (Reasoning)?
Should you use Qwen3.5 397B A17B (Reasoning)?
Only when it fits your setup: GPT-6.1 Sol (Xhigh) is at least as smart for the same money or less, so Qwen3.5 397B A17B (Reasoning) is off the value frontier today.
What is better and cheaper than Qwen3.5 397B A17B (Reasoning)?
GPT-6.1 Sol (Xhigh) — at least as smart for the same money or less.
How much does Qwen3.5 397B A17B (Reasoning) cost?
$0.60/$3.60 in/out per 1M tokens, and $941 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is Qwen3.5 397B A17B (Reasoning) on the Pareto frontier?
No: GPT-6.1 Sol (Xhigh) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where Qwen3.5 397B A17B (Reasoning) is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/qwen3-5-397b-a17b · Markdown: /api/v1/models/qwen3-5-397b-a17b?format=md · llms.txt · agent skill