Qwen3.8-MaxvsClaude Opus 5
Across 7 shared benchmarks, Claude Opus 5 leads overall: Qwen3.8-Max wins 1, Claude Opus 5 wins 6, with 0 ties and an average score difference of -9.98.
Qwen3.8-Max
阿里巴巴 · 2026-08-03 · Reasoning model
Claude Opus 5
Anthropic · 2026-07-24 · Reasoning model
Qwen3.8-Max1 win(14%)(86%)6 winsClaude Opus 5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 7 shared benchmarks.
Coding and Software Engineer
Claude Opus 5 2/2| Benchmark | Qwen3.8-Max | Claude Opus 5 | Diff |
|---|---|---|---|
| DeepSWE | 56.6014 / 27极高强度思考（工具） | 68.804 / 27Max (With Tools) | -12.20 |
| SWE-Bench Pro - Public | 67.705 / 57极高强度思考（工具） | 79.202 / 57Max (With Tools) | -11.50 |
Math and Reasoning
Claude Opus 5 2/2| Benchmark | Qwen3.8-Max | Claude Opus 5 | Diff |
|---|---|---|---|
| FrontierMath Tier 4 v2 | 46.3411 / 34极高强度思考（无工具） | 73.174 / 34最高（无工具） | -26.83 |
| FrontierMath v2 | 74.7411 / 34极高强度思考（无工具） | 85.615 / 34最高（无工具） | -10.88 |
AI Agent - Tool Usage
Qwen3.8-Max 1/1| Benchmark | Qwen3.8-Max | Claude Opus 5 | Diff |
|---|---|---|---|
| AutomationBench | 27.305 / 8极高强度思考（工具） | 266 / 8Max (With Tools) | +1.30 |
General Evaluation
Claude Opus 5 1/1| Benchmark | Qwen3.8-Max | Claude Opus 5 | Diff |
|---|---|---|---|
| GPQA Diamond | 92.6021 / 226极高强度思考（无工具） | 93.889 / 226最高（无工具） | -1.28 |
General Knowledge
Claude Opus 5 1/1| Benchmark | Qwen3.8-Max | Claude Opus 5 | Diff |
|---|---|---|---|
| HLE | 56.2013 / 181极高强度思考（工具） | 64.701 / 181Max (With Tools) | -8.50 |
Specs
| Field | Qwen3.8-Max | Claude Opus 5 |
|---|---|---|
| Publisher | 阿里巴巴 | Anthropic |
| Release date | 2026-08-03 | 2026-07-24 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | Dense |
| Parameters | 2.4T | Not available |
| Context length | 1M | 1M |
| Max output | 128K | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen3.8-Max | Claude Opus 5 |
|---|---|---|
| Text input | ¥12 / 1M tokens | $5 / 1M tokens |
| Text output | ¥36 / 1M tokens | $25 / 1M tokens |
| Cache read | ¥1.5 / 1M tokens | $0.5 / 1M tokens |
| Cache write | Not public | $6.25 / 1M tokens |
Summary
- Qwen3.8-Maxleads in:AI Agent - Tool Usage (1/1)
- Claude Opus 5leads in:Coding and Software Engineer (2/2), Math and Reasoning (2/2), General Evaluation (1/1), General Knowledge (1/1)
On average across the 7 shared benchmarks, Claude Opus 5 scores 9.98 higher.
Largest single-benchmark gap: FrontierMath Tier 4 v2 — Qwen3.8-Max 46.34 vs Claude Opus 5 73.17 (-26.83).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.