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 235B A22B Instruct 2507
Claude Haiku 4.5

Anthropic

Qwen3 235B A22B Instruct 2507

Alibaba (Qwen)

Pricing
Input $/1M$1.00$0.087
Output $/1M$5.00$0.35
Blended $/1M (3:1)$2.00$0.153
Cache read $/1M$0.10$0.018
Cache write $/1M$1.25
Quality indices
Intelligence Index16.912
Coding Index43.9
Math Index71.7
Agentic Index8
Speed & latency
Output speed (tok/s)0
Time to first token0s
Time to first answer token0s
Benchmarks (Artificial Analysis)
MMLU-Pro82.8%
GPQA Diamond75.3%
Humanity's Last Exam11.1%
LiveCodeBench52.4%
MATH-50098.0%
AIME71.7%
AIME 202571.7%
IFBench46.1%
AA-LCR (Long Context Reasoning)33.9%
Terminal-Bench Hard15.2%
τ²-Bench (Telecom)33.3%
Design Arena (Elo)
Website1,1351,070
UI components1,115981
Data viz1,1391,084
SVG1,049
3D1,1011,023
Game dev1,120975
Code categories1,1301,054
ASCII art1,159
Specs
Context window200K262K
Max output tokens64K236K
Input modalitiestext, image, filetext
TokenizerClaudeQwen3