| Claude Fable 5.1 | GPT-6.2 Astra | |
|---|---|---|
| CTO Index | 84.9 (#9) | 88.0 (#4) |
| Provider | Anthropic | OpenAI |
| Weights | Closed | Closed |
| Price $/M in / out | $10 / $50 | $8 / $40 |
| Context window | 1M | 1.1M |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 57.6% | 62.1% |
| WebDev Arena | 1742 | 1766 |
| ARC-AGI-2 | 90.0% | 95.8% |
| Text Arena | 1503 | 1468 |
| ARC-AGI-3 | — | 70.3% |
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Frequently asked questions
Is Claude Fable 5.1 better than GPT-6.2 Astra?
GPT-6.2 Astra scores higher on the CTO Index (88.0 vs 84.9). Across the 4 benchmarks both have results, Claude Fable 5.1 wins 1 (Text Arena) and GPT-6.2 Astra wins 3 (Terminal-Bench, WebDev, ARC-AGI-2). GPT-6.2 Astra costs 20% less per blended token.
Which is better for coding agents, Claude Fable 5.1 or GPT-6.2 Astra?
On Terminal-Bench 4.1, GPT-6.2 Astra scores 62.1% against Claude Fable 5.1's 57.6%. Differences under about three points are within the error bars.
How do Claude Fable 5.1 and GPT-6.2 Astra compare on price?
Claude Fable 5.1 lists at $10 / $50 and GPT-6.2 Astra at $8 / $40 per million input / output tokens.