Claude Fable 5.1 vs GLM-5.3
Claude Fable 5.1 (Anthropic) and GLM-5.3 (Zhipu AI (Z.ai)) compared on price, context window, speed and independent benchmarks. Claude Fable 5.1 scores higher on the Artificial Analysis Intelligence Index (65.7 vs 59.5), while GLM-5.3 is 9.3× cheaper on a blended basis. Pick Claude Fable 5.1 for the hardest tasks and GLM-5.3 when cost dominates.
| Claude Fable 5.1 | GLM-5.3 | |
|---|---|---|
| Provider | Anthropic | Zhipu AI (Z.ai) |
| Input $/1M | $10.0 | $1.40 |
| Output $/1M | $50.0 | $4.40 |
| Blended $/1M (3:1) | $20.0 | $2.15 |
| Cached input $/1M | $0.25 | $0.26 |
| Context window | 1M | 1M |
| Knowledge cutoff | 2026-06 | — |
| License | proprietary | open weights |
| Speed (tok/s) | 71 | 78 |
| Artificial Analysis Intelligence Index | 65.7 | 59.5 |
| LMArena Elo | — | 1474 |
| GPQA Diamond | 93.7% | 91.7% |
| Humanity's Last Exam | 59.1% | 42.3% |