| Claude Opus 5.5 | Claude Fable 5.2 | |
|---|---|---|
| CTO Index | 95.3 (#2) | 95.5 (#1) |
| Provider | Anthropic | Anthropic |
| Weights | Closed | Closed |
| Price $/M in / out | $4 / $20 | $8 / $40 |
| Context window | 1M | 1M |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 65.8% | 65.8% |
| WebDev Arena | 1819 | 1824 |
| ARC-AGI-2 | 93.3% | 93.8% |
| Text Arena | 1506 | 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 Claude Opus 5.5 better than Claude Fable 5.2?
Claude Fable 5.2 scores higher on the CTO Index (95.5 vs 95.3). Across the 4 benchmarks both have results, Claude Opus 5.5 wins 1 (Text Arena) and Claude Fable 5.2 wins 2 (WebDev, ARC-AGI-2). Claude Opus 5.5 costs 50% less per blended token.
Which is better for coding agents, Claude Opus 5.5 or Claude Fable 5.2?
On Terminal-Bench 4.1, Claude Opus 5.5 scores 65.8% against Claude Fable 5.2's 65.8%. Differences under about three points are within the error bars.
How do Claude Opus 5.5 and Claude Fable 5.2 compare on price?
Claude Opus 5.5 lists at $4 / $20 and Claude Fable 5.2 at $8 / $40 per million input / output tokens.