| GLM-5.3-Flash | DeepSeek V4.1 Flash | |
|---|---|---|
| CTO Index | 60.2 (#22) | 66.1 (#20) |
| Provider | Z.ai | DeepSeek |
| Weights | Open weights | Open weights |
| Price $/M in / out | $0.02 / $0.07 | $0.15 / $0.60 |
| Context window | 1M | 1M |
| License | MIT | MIT |
| Terminal-Bench 4.1 | 37.0% | 38.5% |
| WebDev Arena | 1610 | 1658 |
| ARC-AGI-2 | 65.8% | 78.1% |
| Text Arena | 1475 | 1475 |
| ARC-AGI-3 | — | 0.2% |
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Frequently asked questions
Is GLM-5.3-Flash better than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash scores higher on the CTO Index (66.1 vs 60.2). Across the 4 benchmarks both have results, GLM-5.3-Flash wins 0 and DeepSeek V4.1 Flash wins 3 (Terminal-Bench, WebDev, ARC-AGI-2). GLM-5.3-Flash costs 88% less per blended token.
Which is better for coding agents, GLM-5.3-Flash or DeepSeek V4.1 Flash?
On Terminal-Bench 4.1, DeepSeek V4.1 Flash scores 38.5% against GLM-5.3-Flash's 37.0%. Differences under about three points are within the error bars.
How do GLM-5.3-Flash and DeepSeek V4.1 Flash compare on price?
GLM-5.3-Flash lists at $0.02 / $0.07 and DeepSeek V4.1 Flash at $0.15 / $0.60 per million input / output tokens.