| Copilot Fusion | GPT-6.2 Astra | |
|---|---|---|
| CTO Index | 100.0 (Partial) | 88.0 (#4) |
| Provider | GitHub | OpenAI |
| Weights | Closed | Closed |
| Price $/M in / out | Not listed | $8 / $40 |
| Context window | Not listed | 1.1M |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 71.2% | 62.1% |
| WebDev Arena | — | 1766 |
| ARC-AGI-2 | — | 95.8% |
| Text Arena | — | 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 Copilot Fusion better than GPT-6.2 Astra?
Copilot Fusion scores higher on the CTO Index (100.0 vs 88.0). Across the 1 benchmarks both have results, Copilot Fusion wins 1 (Terminal-Bench) and GPT-6.2 Astra wins 0.
Which is better for coding agents, Copilot Fusion or GPT-6.2 Astra?
On Terminal-Bench 4.1, Copilot Fusion scores 71.2% against GPT-6.2 Astra's 62.1%. Differences under about three points are within the error bars.
How do Copilot Fusion and GPT-6.2 Astra compare on price?
Copilot Fusion lists at Not listed and GPT-6.2 Astra at $8 / $40 per million input / output tokens.