| Beam 1.0 | Gemini 4 Carbon | |
|---|---|---|
| CTO Index | 27.7 (#39) | 92.4 (#3) |
| Provider | Reflection AI | |
| Weights | Open weights | Closed |
| Price $/M in / out | $0.30 / $1 | $2 / $10 |
| Context window | 1M | Not listed |
| License | Apache 2.0 | Proprietary |
| Terminal-Bench 4.1 | 6.4% | 64.5% |
| WebDev Arena | 1437 | 1769 |
| ARC-AGI-2 | 23.5% | 94.2% |
| Text Arena | 1434 | 1527 |
| ARC-AGI-3 | — | 65.1% |
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Frequently asked questions
Is Beam 1.0 better than Gemini 4 Carbon?
Gemini 4 Carbon scores higher on the CTO Index (92.4 vs 27.7). Across the 4 benchmarks both have results, Beam 1.0 wins 0 and Gemini 4 Carbon wins 4 (Terminal-Bench, WebDev, ARC-AGI-2, Text Arena). Beam 1.0 costs 88% less per blended token.
Which is better for coding agents, Beam 1.0 or Gemini 4 Carbon?
On Terminal-Bench 4.1, Gemini 4 Carbon scores 64.5% against Beam 1.0's 6.4%. Differences under about three points are within the error bars.
How do Beam 1.0 and Gemini 4 Carbon compare on price?
Beam 1.0 lists at $0.30 / $1 and Gemini 4 Carbon at $2 / $10 per million input / output tokens.