Qwen 3.6 Plus PreviewvsQwen3.5-397B-A17B
Across 15 shared benchmarks, Qwen 3.6 Plus Preview leads overall: Qwen 3.6 Plus Preview wins 12, Qwen3.5-397B-A17B wins 3, with 0 ties and an average score difference of +2.33.
Qwen 3.6 Plus Preview
阿里巴巴 · 2026-03-31 · Chat model
Qwen3.5-397B-A17B
阿里巴巴 · 2026-02-16 · Multimodal model
Qwen 3.6 Plus Preview12 wins(80%)(20%)3 winsQwen3.5-397B-A17B
Benchmark scores
Grouped by capability, sorted by largest gap within each. 15 shared benchmarks.
Coding and Software Engineer
Qwen 3.6 Plus Preview 4/4| Benchmark | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 56.6020 / 54Thinking (With Tools) | 50.9039 / 54Thinking (No Tools) | +5.70 |
| SWE-bench Multilingual | 73.809 / 23Thinking (No Tools) | 69.3020 / 23Thinking (No Tools) | +4.50 |
| LiveCodeBench | 87.1010 / 123Thinking (No Tools) | 83.6020 / 123Thinking (No Tools) | +3.50 |
| SWE-bench Verified | 78.8021 / 112Thinking (With Tools) | 76.4033 / 112Thinking (With Tools) | +2.40 |
General Knowledge
Qwen 3.6 Plus Preview 4/4| Benchmark | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B | Diff |
|---|---|---|---|
| HLE | 50.6024 / 172Thinking (With Tools) | 48.3035 / 172Thinking (With Tools + Internet) | +2.30 |
| GPQA Diamond | 90.4019 / 187Thinking (No Tools) | 88.4029 / 187Thinking (No Tools) | +2 |
| MMLU Pro | 88.505 / 132Thinking (No Tools) | 87.8010 / 132Thinking (No Tools) | +0.70 |
| C-Eval | 93.302 / 10Thinking (No Tools) | 933 / 10Thinking (No Tools) | +0.30 |
AI Agent - Tool Usage
Qwen 3.6 Plus Preview 2/2| Benchmark | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 61.6016 / 47Thinking (With Tools) | 52.5030 / 47Thinking (With Tools) | +9.10 |
| Tool Decathlon | 39.806 / 9Thinking (With Tools) | 38.307 / 9Thinking (With Tools) | +1.50 |
Long Context
Qwen3.5-397B-A17B 2/2| Benchmark | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B | Diff |
|---|---|---|---|
| LongBench v2 | 623 / 11Normal (No Tools) | 63.202 / 11Normal (No Tools) | -1.20 |
| AA-LCR | 68.308 / 15Thinking (No Tools) | 68.707 / 15Thinking (No Tools) | -0.40 |
Math and Reasoning
Qwen 3.6 Plus Preview 2/2| Benchmark | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B | Diff |
|---|---|---|---|
| AIME 2026 | 95.304 / 18Thinking (No Tools) | 91.3013 / 18Thinking (No Tools) | +4 |
| IMO-AnswerBench | 83.8012 / 21Thinking (No Tools) | 80.9017 / 21Thinking (No Tools) | +2.90 |
Instruction Following
Qwen3.5-397B-A17B 1/1| Benchmark | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B | Diff |
|---|---|---|---|
| IF Bench | 74.207 / 30Thinking (No Tools) | 76.504 / 30Thinking (No Tools) | -2.30 |
Specs
| Field | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B |
|---|---|---|
| Publisher | 阿里巴巴 | 阿里巴巴 |
| Release date | 2026-03-31 | 2026-02-16 |
| Model type | Chat model | Multimodal model |
| Architecture | Dense | MoE |
| Parameters | Not available | 39.7B |
| Context length | 1M | 256K |
| Max output | 64K | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen 3.6 Plus Preview | Qwen3.5-397B-A17B |
|---|---|---|
| Text input | $0.5 / 1M tokens | $0.5 / 1M tokens |
| Text output | $3 / 1M tokens | $3 / 1M tokens |
| Cache read | $0.05 / 1M tokens | $0.05 / 1M tokens |
| Cache write | $0.625 / 1M tokens | $0.625 / 1M tokens |
Summary
- Qwen 3.6 Plus Previewleads in:Coding and Software Engineer (4/4), General Knowledge (4/4), AI Agent - Tool Usage (2/2), Math and Reasoning (2/2)
- Qwen3.5-397B-A17Bleads in:Long Context (2/2), Instruction Following (1/1)
On average across the 15 shared benchmarks, Qwen 3.6 Plus Preview scores 2.33 higher.
Largest single-benchmark gap: Terminal Bench 2.0 — Qwen 3.6 Plus Preview 61.60 vs Qwen3.5-397B-A17B 52.50 (+9.10).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.