modelgrep

Anthropic: Claude Sonnet 5 vs MoonshotAI: Kimi K2.7 Code

anthropic logoAnthropic: Claude Sonnet 5anthropic/claude-sonnet-5VSmoonshotai logoMoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code

Anthropic: Claude Sonnet 5 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Sonnet 5MoonshotAI: Kimi K2.7 Code
Intelligence Index53.4✓41.9
Coding Index71.5✓60.8
GPQA Diamond91%✓90%
Design Arena Elo1330✓1319
Speed (tokens/sec)73108✓
Latency2.5s518ms✓
Input price /M$2.00$0.740✓
Output price /M$10.00$3.50✓
Context window1M✓262K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSONVision
Anthropic: Claude Sonnet 5 details →MoonshotAI: Kimi K2.7 Code details →