| Claude Opus 5 | Gemini 4 Carbon | |
|---|---|---|
| CTO Index | 78.9 (#13) | 92.4 (#3) |
| Provider | Anthropic | |
| Weights | Closed | Closed |
| Price $/M in / out | $5 / $25 | $2 / $10 |
| Context window | 1M | Not listed |
| License | Proprietary | Proprietary |
| Terminal-Bench 4.1 | 53.3% | 64.5% |
| WebDev Arena | 1692 | 1769 |
| ARC-AGI-2 | 90.4% | 94.2% |
| Text Arena | 1490 | 1527 |
| ARC-AGI-3 | 30.2% | 65.1% |
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Frequently asked questions
Is Claude Opus 5 better than Gemini 4 Carbon?
Gemini 4 Carbon scores higher on the CTO Index (92.4 vs 78.9). Across the 5 benchmarks both have results, Claude Opus 5 wins 0 and Gemini 4 Carbon wins 5 (Terminal-Bench, WebDev, ARC-AGI-2, Text Arena, ARC-AGI-3). Gemini 4 Carbon costs 60% less per blended token.
Which is better for coding agents, Claude Opus 5 or Gemini 4 Carbon?
On Terminal-Bench 4.1, Gemini 4 Carbon scores 64.5% against Claude Opus 5's 53.3%. Differences under about three points are within the error bars.
How do Claude Opus 5 and Gemini 4 Carbon compare on price?
Claude Opus 5 lists at $5 / $25 and Gemini 4 Carbon at $2 / $10 per million input / output tokens.