Qwen3.5 4B vs Qwen3.5 397B A17B: Release Comparison
Comparison of the Qwen3.5 4B and Qwen3.5 397B A17B releases: 2 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 4 models.
- For intelligence, Qwen3.5 397B A17B scores highest: Qwen3.5 397B A17B (Non-reasoning) at 21, against Qwen3.5 4B (Reasoning) at 13 for Qwen3.5 4B.
- For output speed, Qwen3.5 397B A17B is fastest: Qwen3.5 397B A17B (Non-reasoning) at 86 t/s, against Qwen3.5 4B (Reasoning) at 21 t/s for Qwen3.5 4B.
Releases compared
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost per Task (USD, Log Scale)
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
Further details
Input modality | Output modality | Weights | Provider Benchmarks | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5 397B A17B (Non-reasoning) |  Alibaba | 21 | - | - | - | - | - | - | - | $0.9 | $0.60 | $3.60 | - | - | - | - | - | 86 | 2.20s | 2.20s | 8.01s | - | 397B 17B active at inference time | 262k | Feb 2026 | - | No | Supports: text and image | Supports: text |   +3 | |||
| Qwen3.5 397B A17B (Reasoning) | Alibaba | 18 | 19 | 15 | 21 | - | 21 | 27 | $0.47 | $0.9 | $0.60 | $3.60 | - | $941 | 19k | 9k | 95M | 86 | 2.26s | 39.35s | 45.17s | 181.37s | 397B 17B active at inference time | 262k | Feb 2026 | - | Yes | Supports: text and image | Supports: text |  +5 | |||
| Qwen3.5 4B (Reasoning) | Alibaba | 13 | - | - | - | - | - | - | - | $0.0 | $0.03 | $0.15 | - | - | - | - | - | 21 | 0.74s | 98.08s | 122.41s | - | 4.7B | 262k | Mar 2026 | - | Yes | Supports: text, image, and video | Supports: text | | |||
| Qwen3.5 4B (Non-reasoning) | Alibaba | 11 | - | - | - | - | - | - | - | $0.0 | $0.03 | $0.15 | - | - | - | - | - | 15 | 0.87s | 0.87s | 33.31s | - | 4.7B | 262k | Mar 2026 | - | No | Supports: text, image, and video | Supports: text | | |||