Claude Opus 4.8 vs Qwen3.7 Max: Benchmarks, Pricing & Capabilities Compared
TL;DR — Claude Opus 4.8 wins for general use · Qwen3.7 Max wins for cost.
Claude Opus 4.8 Anthropic
- Released
- 2026-05-28
- Context window
- 1M tokens
- Input price
- $6.25 / Mtok
- Output price
- $25.00 / Mtok
Qwen3.7 Max Alibaba
- Released
- 2026-05-19
- Context window
- 1M tokens
- Input price
- $2.50 / Mtok
- Output price
- $7.50 / Mtok
Benchmark comparison
| Benchmark | Claude Opus 4.8 | Qwen3.7 Max |
|---|---|---|
| AA Intelligence Index | 61.4 ✓ | 56.6 |
| GPQA Diamond | 92.0% | 92.3% ✓ |
| HLE | 45.7% ✓ | 38.1% |
| IF-Bench | 62.2% | 80.5% ✓ |
| LiveCodeBench Reasoning | 67.7% | 69.0% ✓ |
| SciCode | 53.5% ✓ | 48.8% |
| TAU2-bench | 94.4% | 94.7% ✓ |
| TerminalBench-Hard | 58.3% ✓ | 50.8% |
Pricing comparison
| Metric | Claude Opus 4.8 | Qwen3.7 Max |
|---|---|---|
| Input ($/Mtok) | $6.25 | $2.50 |
| Output ($/Mtok) | $25.00 | $7.50 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $31.25 | $10.00 |
Context window & modalities
| Attribute | Claude Opus 4.8 | Qwen3.7 Max |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input modalities | text, image | text |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ Qwen3.7 Max
Basis: GPQA Diamond
Claude Opus 4.8 92% vs Qwen3.7 Max 92.3% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
Tie
Basis: Context window
Claude Opus 4.8 1M tokens vs Qwen3.7 Max 1M tokens.
Cost
→ Qwen3.7 Max
Basis: Input $/Mtok
Claude Opus 4.8 $6.25/Mtok vs Qwen3.7 Max $2.5/Mtok input.
Changelog & releases
Claude Opus 4.8
Released 2026-05-28
Qwen3.7 Max
Released 2026-05-19