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 Opus 4.6o3
Claude Opus 4.6

Anthropic

o3

OpenAI

Pricing
Input $/1M$5.00$2.00
Output $/1M$25.00$8.00
Blended $/1M (3:1)$10.00$3.50
Cache read $/1M$0.50$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index37.830.4
Coding Index
Math Index88.3
Agentic Index
Speed & latency
Output speed (tok/s)57159
Time to first token1.85s4.84s
Time to first answer token1.85s4.84s
Benchmarks (Artificial Analysis)
MMLU-Pro85.3%
GPQA Diamond84.0%82.7%
Humanity's Last Exam18.6%20.0%
LiveCodeBench80.8%
SciCode45.7%41.0%
MATH-50099.2%
AIME90.3%
AIME 202588.3%
IFBench44.6%71.4%
AA-LCR (Long Context Reasoning)58.3%69.3%
Terminal-Bench Hard48.5%37.1%
τ²-Bench (Telecom)84.8%80.7%
Design Arena (Elo)
Website1,3231,064
Web apps1,261
Full-stack1,279
Mobile apps1,280
Android native1,195
UI components1,3361,060
Data viz1,3221,200
SVG1,274
3D1,335
Game dev1,3371,093
Code categories1,3271,053
ASCII art1,298
Specs
Context window1M200K
Max output tokens128K100K
Input modalitiestext, image, fileimage, text, file
TokenizerClaudeGPT