Qwen3.7 MaxvsClaude Opus 4.6
Across 11 shared benchmarks, Qwen3.7 Max leads overall: Qwen3.7 Max wins 6, Claude Opus 4.6 wins 5, with 0 ties and an average score difference of -0.16.
Qwen3.7 Max
阿里巴巴 · 2026-05-20 · Reasoning model
Claude Opus 4.6
Anthropic · 2026-02-05 · Reasoning model
Qwen3.7 Max6 wins(55%)(45%)5 winsClaude Opus 4.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 11 shared benchmarks.
Coding and Software Engineer
Even 4/4| Benchmark | Qwen3.7 Max | Claude Opus 4.6 | Diff |
|---|---|---|---|
| LiveCodeBench | 91.604 / 126最高（无工具） | 7640 / 126Extended (no tools) | +15.60 |
| Text Arena (Coding) | 1,54111 / 35Normal (No Tools) | 1,5558 / 35Normal (No Tools) | -14.58 |
| SWE-bench Multilingual | 78.304 / 25Thinking (With Tools) | 7215 / 25Extended (with tools) | +6.30 |
| SWE-bench Verified | 80.4013 / 114Thinking (With Tools) | 80.8410 / 114Extended (with tools) | -0.44 |
AI Agent - Tool Usage
Even 2/2| Benchmark | Qwen3.7 Max | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 69.705 / 48Thinking (With Tools) | 65.4011 / 48Extended (with tools) | +4.30 |
| MCP-Atlas | 76.4016 / 38Thinking (With Tools) | 76.8013 / 38Deep Thinking (With Tools) | -0.40 |
General Knowledge
Even 2/2| Benchmark | Qwen3.7 Max | Claude Opus 4.6 | Diff |
|---|---|---|---|
| LiveBench | 74.2921 / 115Deep Thinking (No Tools) | 76.338 / 115Thinking High (No Tools) | -2.04 |
| HLE | 53.5018 / 181Thinking (With Tools) | 5320 / 181Extended (with tools, internet) | +0.50 |
Commonsense Reasoning
Qwen3.7 Max 1/1| Benchmark | Qwen3.7 Max | Claude Opus 4.6 | Diff |
|---|---|---|---|
| SimpleBench | 70.407 / 67Normal (No Tools) | 67.609 / 67Normal (No Tools) | +2.80 |
General Evaluation
Qwen3.7 Max 1/1| Benchmark | Qwen3.7 Max | Claude Opus 4.6 | Diff |
|---|---|---|---|
| GPQA Diamond | 92.4022 / 226最高（无工具） | 91.3128 / 226Extended (no tools) | +1.09 |
Instruction Following
Claude Opus 4.6 1/1| Benchmark | Qwen3.7 Max | Claude Opus 4.6 | Diff |
|---|---|---|---|
| IF Bench | 79.104 / 33最高（无工具） | 941 / 33Extended (no tools) | -14.90 |
Specs
| Field | Qwen3.7 Max | Claude Opus 4.6 |
|---|---|---|
| Publisher | 阿里巴巴 | Anthropic |
| Release date | 2026-05-20 | 2026-02-05 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1000K |
| Max output | 64K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen3.7 Max | Claude Opus 4.6 |
|---|---|---|
| Text input | ¥12 / 1M tokens | $0.5 / 1M tokens |
| Text output | ¥36 / 1M tokens | $25 / 1M tokens |
| Cache read | Not public | $0.5 / 1M tokens |
| Cache write | Not public | $10 / 1M tokens |
Summary
- Qwen3.7 Maxleads in:Commonsense Reasoning (1/1), General Evaluation (1/1)
- Claude Opus 4.6leads in:Instruction Following (1/1)
- Tied in:Coding and Software Engineer, AI Agent - Tool Usage, General Knowledge
On average across the 11 shared benchmarks, Claude Opus 4.6 scores 0.16 higher.
Largest single-benchmark gap: LiveCodeBench — Qwen3.7 Max 91.60 vs Claude Opus 4.6 76 (+15.60).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.