| GPT-6 Astra | Claude Opus 5.5 | |
|---|---|---|
| CTO Index | 87.2 (#6) | 95.3 (#2) |
| Provider | OpenAI | Anthropic |
| Weights | Closed | Closed |
| Price $/M in / out | $10 / $50 | $4 / $20 |
| Context window | 1.1M | 1M |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 60.3% | 65.8% |
| WebDev Arena | 1764 | 1819 |
| ARC-AGI-2 | 95.0% | 93.3% |
| Text Arena | 1475 | 1506 |
| ARC-AGI-3 | 62.7% | — |
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Frequently asked questions
Is GPT-6 Astra better than Claude Opus 5.5?
Claude Opus 5.5 scores higher on the CTO Index (95.3 vs 87.2). Across the 4 benchmarks both have results, GPT-6 Astra wins 1 (ARC-AGI-2) and Claude Opus 5.5 wins 3 (Terminal-Bench, WebDev, Text Arena). Claude Opus 5.5 costs 60% less per blended token.
Which is better for coding agents, GPT-6 Astra or Claude Opus 5.5?
On Terminal-Bench 4.1, Claude Opus 5.5 scores 65.8% against GPT-6 Astra's 60.3%. Differences under about three points are within the error bars.
How do GPT-6 Astra and Claude Opus 5.5 compare on price?
GPT-6 Astra lists at $10 / $50 and Claude Opus 5.5 at $4 / $20 per million input / output tokens.