AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Haiku 4.5Qwen3.6 Plus
Claude Haiku 4.5

Anthropic

Qwen3.6 Plus

Alibaba (Qwen)

Pricing
Input $/1M$1.00$0.325
Output $/1M$5.00$1.95
Blended $/1M (3:1)$2.00$0.731
Cache read $/1M$0.10
Cache write $/1M$1.25$0.406
Quality indices
Intelligence Index29.639.6
Coding Index43.954.5
Math Index
Agentic Index16.427.6
Speed & latency
Output speed (tok/s)52
Time to first token1.73s
Time to first answer token107.62s
Benchmarks (Artificial Analysis)
GPQA Diamond88.2%
Humanity's Last Exam25.7%
SciCode40.7%
IFBench75.2%
AA-LCR (Long Context Reasoning)69.7%
Terminal-Bench Hard43.9%
Terminal-Bench 2.161.4%
τ²-Bench (Telecom)97.7%
τ³-Bench Banking16.5%
Design Arena (Elo)
Website1,1491,247
UI components1,1421,271
Data viz1,1601,255
SVG1,0721,207
3D1,1311,254
Game dev1,1551,262
Code categories1,1481,257
ASCII art1,1821,165
Specs
Context window200K1M
Max output tokens64K66K
Input modalitiestext, image, filetext, image, video
TokenizerClaudeQwen3