| Mistral Large 4 | GPT-6.2 Astra | |
|---|---|---|
| CTO Index | 46.6 (#35) | 88.0 (#4) |
| Provider | Mistral | OpenAI |
| Weights | Open weights | Closed |
| Price $/M in / out | $0.70 / $2.10 | $8 / $40 |
| Context window | 1M | 1.1M |
| License | Modified MIT | Proprietary |
| Terminal-Bench 4.1 | 27.6% | 62.1% |
| WebDev Arena | 1573 | 1766 |
| ARC-AGI-2 | — | 95.8% |
| Text Arena | 1423 | 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 Mistral Large 4 better than GPT-6.2 Astra?
GPT-6.2 Astra scores higher on the CTO Index (88.0 vs 46.6). Across the 3 benchmarks both have results, Mistral Large 4 wins 0 and GPT-6.2 Astra wins 3 (Terminal-Bench, WebDev, Text Arena). Mistral Large 4 costs 93% less per blended token.
Which is better for coding agents, Mistral Large 4 or GPT-6.2 Astra?
On Terminal-Bench 4.1, GPT-6.2 Astra scores 62.1% against Mistral Large 4's 27.6%. Differences under about three points are within the error bars.
How do Mistral Large 4 and GPT-6.2 Astra compare on price?
Mistral Large 4 lists at $0.70 / $2.10 and GPT-6.2 Astra at $8 / $40 per million input / output tokens.