modelgrep

Anthropic: Claude Sonnet 4.5 vs Qwen: Qwen3.5-122B-A10B

Anthropic: Claude Sonnet 4.5 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Sonnet 4.5Qwen: Qwen3.5-122B-A10B
Intelligence Index37.135.9
Coding Index33.531.6
GPQA Diamond73%83%
Design Arena Elo1242
Speed (tokens/sec)4686
Latency892ms984ms
Input price /M$3.00$0.260
Output price /M$15.00$2.08
Context window1M262K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSONVision