Claude 4.5 Haiku (Reasoning) vs Qwen3.5 122B A10B (Non-reasoning)

Anthropic · Alibaba · catalog 2026-09-14

Qwen3.5 122B A10B (Non-reasoning) beats Claude 4.5 Haiku (Reasoning): cheaper ($0.68 vs $0.77/M) and at least as smart (index 17.7 vs 17.6).
Claude 4.5 Haiku (Reasoning)Qwen3.5 122B A10B (Non-reasoning)
Speed (tok/s)85 measured138 measured
Blended $/M$0.77 derived$0.68 derived
Intelligence index17.6 measured17.7 measured
TTFT (ms)1789 measured231 measured
Context——
Coding index44 measured43 measured
Agentic indexnot measured for both

Claude 4.5 Haiku (Reasoning) card · Qwen3.5 122B A10B (Non-reasoning) card · 3D observatory

Verdicts use price×intelligence dominance only, and only where both sides are measured; null cells stay null with their provenance (em-dash = not in catalog). Percentile-free by design — this page compares two models, not the field. Generated page — do not hand-edit.