Up to four models
Claude Opus 5.5 vs Qwen3.8-Flash-Next
On the index (GPT-4 = 100), Claude Opus 5.5 scores 195 and Qwen3.8-Flash-Next 162. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Opus 5.5
195178–211
WeightsClosed
ReleasedSep 2026
Price in / out$4.0 / $20
Context1M
Core tests taken6 of 9
162131–193
WeightsOpen
ReleasedAug 2026
Price in / out–
Context–
Core tests taken0 of 9
Claude Opus 5.5 leads Qwen3.8-Flash-Next by 33 points.
Test by testthird-party results
Claude Opus 5.5
Qwen3.8-Flash-Next
Every result as a table
| Test | Claude Opus 5.5 | Qwen3.8-Flash-Next |
|---|---|---|
| Reasoning & knowledge | ||
| LiveBench Data Analysis | 80.3% | 74.2% |
| LiveBench IF | 67.0% | 77.1% |
| LiveBench Language | 86.3% | 74.6% |
| LiveBench Reasoning | 92.2% | 87.4% |
| Maths | ||
| LiveBench Mathematics | 97.1% | 85.8% |
| Coding | ||
| LiveBench Agentic Coding | 71.7% | 61.6% |
| LiveBench Coding | 89.3% | 72.5% |
Tests at least two of these models have taken. Bold rows are the core tests.