Benchmark avg
64.5
5 tracked scores
Model portfolio
Tap a star to rate
Alibaba · Released 2026-02-15 · v2026-02-15 · Closed · Context 262K tokens
Language Cap
148
Cadle Language Cap 148 · 40%
Benchmark average
—
Not enough benchmark results yet
Pricing
$0.60
$3.60 / 1M out
Only measured signals
Benchmark avg
64.5
5 tracked scores
Strongest signal
otis-mock-aime-2024-2025
Score 88.9
Blended $/1M
$4.20
In $0.60 · Out $3.60
Value index
15.4
Quality ÷ blended $/1M (higher is better)
Context
262K
Provider context window (not max output)
Measured matrix and verified gateway observations only.
PROVIDER
Alibaba
RELEASE
2026-02-15
CONTEXT
262K tokens
STATUS
ACTIVE
Real operator evaluations, prompt robustness observations, and deployment notes for Qwen3.5 397B-A17B.
Tested Qwen3.5 397B-A17B on high-concurrency tool loops. Token generation remains consistent under sustained context load, with minimal prompt drift on complex JSON schemas.
Evaluated Qwen3.5 397B-A17B on multi-turn code synthesis. Code reasoning and diff application succeed on ~88% of test suites. Best paired with strict system prompt guardrails.
| Metric | |
|---|---|
| Provider | Alibaba |
| Release | 2026-02-15 |
| Input / 1M | $0.60 |
| Output / 1M | $3.60 |
| Context | 262K tokens |
| Cadle Cap | 148 |
| Cap board | Cadle Language Cap 148 |
| apex-agents | 24.9 |
| lmca | 44.6 |
| dtbench | 79.1 |
| otis-mock-aime-2024-2025 | 88.9 |
| gpqa-diamond | 85.2 |
Scores may use different scales — check the Benchmarks tab for source links.
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
Alibaba listing
Source: Epoch AI (CC BY 4.0) · LMArena (CC BY 4.0) · as of 2026-10-31 · All credits