| Qwen3.8-Max | Claude Fable 5.2 | |
|---|---|---|
| CTO Index | 57.1 (#25) | 95.5 (#1) |
| Provider | Alibaba | Anthropic |
| Weights | Closed | Closed |
| Price $/M in / out | $2 / $6 | $8 / $40 |
| Context window | 1M | 1M |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 27.0% | 65.8% |
| WebDev Arena | 1674 | 1824 |
| ARC-AGI-2 | — | 93.8% |
| Text Arena | 1484 | 1503 |
| ARC-AGI-3 | — | 81.2% |
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Frequently asked questions
Is Qwen3.8-Max better than Claude Fable 5.2?
Claude Fable 5.2 scores higher on the CTO Index (95.5 vs 57.1). Across the 3 benchmarks both have results, Qwen3.8-Max wins 0 and Claude Fable 5.2 wins 3 (Terminal-Bench, WebDev, Text Arena). Qwen3.8-Max costs 81% less per blended token.
Which is better for coding agents, Qwen3.8-Max or Claude Fable 5.2?
On Terminal-Bench 4.1, Claude Fable 5.2 scores 65.8% against Qwen3.8-Max's 27.0%. Differences under about three points are within the error bars.
How do Qwen3.8-Max and Claude Fable 5.2 compare on price?
Qwen3.8-Max lists at $2 / $6 and Claude Fable 5.2 at $8 / $40 per million input / output tokens.