Gemma 4 31B vs Qwen3.5 397B A17B: Release Comparison
Comparison of the Gemma 4 31B 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 Gemma 4 31B (Reasoning) at 19 for Gemma 4 31B.
- For output speed, Qwen3.5 397B A17B is fastest: Qwen3.5 397B A17B (Non-reasoning) at 87 t/s, against Gemma 4 31B (Reasoning) at 35 t/s for Gemma 4 31B.
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 | - | - | - | - | - | 87 | 2.20s | 2.20s | 7.97s | - | 397B 17B active at inference time | 262k | Feb 2026 | - | No | Supports: text and image | Supports: text |   +3 | |||
| Gemma 4 31B (Reasoning) |  Google | 19 | - | - | - | - | 17 | 21 | - | $0.0 | $0.00 | $0.00 | - | - | - | - | - | 35 | 1.03s | 50.09s | 64.22s | - | 30.7B | 256k | Apr 2026 | - | Yes | Supports: text, image, and video | Supports: text |    +11 | |||
| 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 | 39.22s | 45.02s | 176.81s | 397B 17B active at inference time | 262k | Feb 2026 | - | Yes | Supports: text and image | Supports: text |  +6 | |||
| Gemma 4 31B (Non-reasoning) | Google | 14 | - | - | - | - | - | - | - | $0.2 | $0.14 | $0.40 | $0.14 | - | - | - | - | 34 | 2.22s | 2.22s | 17.05s | - | 30.7B | 256k | Apr 2026 | - | No | Supports: text, image, and video | Supports: text |  +8 | |||