Claude Fable 5 vs Kimi K3
Claude Fable 5 (Anthropic) and Kimi K3 (Moonshot AI) compared on price, context window, speed and independent benchmarks. Claude Fable 5 scores higher on the Artificial Analysis Intelligence Index (62.1 vs 59.7), while Kimi K3 is 3.3× cheaper on a blended basis. Pick Claude Fable 5 for the hardest tasks and Kimi K3 when cost dominates.
| Claude Fable 5 | Kimi K3 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Input $/1M | $10.0 | $3.00 |
| Output $/1M | $50.0 | $15.0 |
| Blended $/1M (3:1) | $20.0 | $6.00 |
| Cached input $/1M | $1.00 | $0.30 |
| Context window | 1M | 1.0M |
| Knowledge cutoff | 2026-01 | — |
| License | proprietary | open weights |
| Speed (tok/s) | 68 | 38 |
| Artificial Analysis Intelligence Index | 62.1 | 59.7 |
| LMArena Elo | 1494 | 1476 |
| GPQA Diamond | 92.6% | 93.5% |
| AIME | 99.7%* | — |
| SWE-bench Verified | 95% | 93.4% |
| MMLU-Pro | 91.5%* | — |
| Humanity's Last Exam | 55.5% | 46.9% |
| MMMU | — | 81.6% |