modelgrep

Anthropic: Claude Opus 4.6 vs Qwen: Qwen3.6 Max Preview

Anthropic: Claude Opus 4.6 wins on more metrics (7 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Opus 4.6Qwen: Qwen3.6 Max Preview
Intelligence Index52.951.8
Coding Index48.144.9
GPQA Diamond90%89%
Design Arena Elo1358
Speed (tokens/sec)4544
Latency1.6s1.7s
Input price /M$5.00$1.04
Output price /M$25.00$6.24
Context window1M262K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSON