| Hy4 | Claude Fable 5.2 | |
|---|---|---|
| CTO Index | 53.4 (Partial) | 95.5 (#1) |
| Provider | Tencent | Anthropic |
| Weights | Closed | Closed |
| Price $/M in / out | Not listed | $8 / $40 |
| Context window | Not listed | 1M |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 37.9% | 65.8% |
| WebDev Arena | 1650 | 1824 |
| ARC-AGI-2 | — | 93.8% |
| Text Arena | — | 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 Hy4 better than Claude Fable 5.2?
Claude Fable 5.2 scores higher on the CTO Index (95.5 vs 53.4). Across the 2 benchmarks both have results, Hy4 wins 0 and Claude Fable 5.2 wins 2 (Terminal-Bench, WebDev).
Which is better for coding agents, Hy4 or Claude Fable 5.2?
On Terminal-Bench 4.1, Claude Fable 5.2 scores 65.8% against Hy4's 37.9%. Differences under about three points are within the error bars.
How do Hy4 and Claude Fable 5.2 compare on price?
Hy4 lists at Not listed and Claude Fable 5.2 at $8 / $40 per million input / output tokens.