Claude Opus 4.7 vs Kimi Linear 48B A3B Instruct
Anthropic vs Moonshot AI — benchmarks, pricing, and capabilities side by side.
- •Claude Opus 4.7 has the higher intelligence index (90.9 vs 43.5)
- •Kimi Linear 48B A3B Instruct is cheaper ($0.00 vs $5.00 per 1M input)
| Claude Opus 4.7 | Kimi Linear 48B A3B Instruct | |
|---|---|---|
| Intelligence index | 90.9 | 43.5 |
| Developer | Anthropic | Moonshot AI |
| Type | LLM | LLM |
| Access | API only | — |
| Context window | 1,000,000 tokens | — |
| Input price | $5.00 / 1M | $0.00 / 1M |
| Output price | $25.00 / 1M | $0.00 / 1M |
| Speed | 49 tok/s | — |
| Released | April 16, 2026 | October 30, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image | — |
| Output modalities | Text | — |
Shared benchmarks
Claude Opus 4.7
Kimi Linear 48B A3B Instruct
GPQA Diamond
94.2
41.2
Humanity’s Last Exam
39.6
2.7