| GPT-6 Luna | Claude Haiku 5.5 | |
|---|---|---|
| CTO Index | 44.9 (#37) | 57.1 (#24) |
| Provider | OpenAI | Anthropic |
| Weights | Closed | Closed |
| Price $/M in / out | $0.10 / $0.50 | $0.10 / $0.50 |
| Context window | 1.1M | 1M |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 15.2% | 40.0% |
| WebDev Arena | 1578 | 1595 |
| ARC-AGI-2 | 59.3% | 61.3% |
| Text Arena | 1443 | 1421 |
| ARC-AGI-3 | 0.2% | 0.5% |
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Frequently asked questions
Is GPT-6 Luna better than Claude Haiku 5.5?
Claude Haiku 5.5 scores higher on the CTO Index (57.1 vs 44.9). Across the 5 benchmarks both have results, GPT-6 Luna wins 1 (Text Arena) and Claude Haiku 5.5 wins 4 (Terminal-Bench, WebDev, ARC-AGI-2, ARC-AGI-3).
Which is better for coding agents, GPT-6 Luna or Claude Haiku 5.5?
On Terminal-Bench 4.1, Claude Haiku 5.5 scores 40.0% against GPT-6 Luna's 15.2%. Differences under about three points are within the error bars.
How do GPT-6 Luna and Claude Haiku 5.5 compare on price?
GPT-6 Luna lists at $0.10 / $0.50 and Claude Haiku 5.5 at $0.10 / $0.50 per million input / output tokens.