modelgrep

Anthropic: Claude Haiku 4.5 vs Qwen: Qwen3.6 35B A3B

Qwen: Qwen3.6 35B A3B wins on more metrics (7 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Haiku 4.5Qwen: Qwen3.6 35B A3B
Intelligence Index31.031.5
Coding Index29.617.6
GPQA Diamond65%82%
Design Arena Elo1182
Speed (tokens/sec)90165
Latency628ms257ms
Input price /M$1.00$0.150
Output price /M$5.00$1.00
Context window200K262K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSONVision