modelgrep

Anthropic: Claude Sonnet 4.6 vs Qwen: Qwen3.7 Plus

Qwen: Qwen3.7 Plus wins on more metrics (6 of 8), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Sonnet 4.6Qwen: Qwen3.7 Plus
Intelligence Index42.653.3
Coding Index43.046.5
GPQA Diamond80%90%
Design Arena Elo1329
Speed (tokens/sec)4434
Latency1.3s1.0s
Input price /M$3.00$0.320
Output price /M$15.00$1.28
Context window1M1M
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSONVision