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 4.6GPT-4o
Claude Opus 4.6

Anthropic

GPT-4o

OpenAI

Pricing
Input $/1M$5.00$2.50
Output $/1M$25.00$10.00
Blended $/1M (3:1)$10.00$4.38
Cache read $/1M$0.50$1.25
Cache write $/1M$6.25
Quality indices
Intelligence Index26.48.4
Coding Index
Math Index6
Agentic Index
Speed & latency
Output speed (tok/s)00
Time to first token0s0s
Time to first answer token0s0s
Benchmarks (Artificial Analysis)
MMLU-Pro74.8%
GPQA Diamond84.0%54.3%
Humanity's Last Exam19.1%2.4%
LiveCodeBench30.9%
MATH-50075.9%
AIME15.0%
AIME 20256.0%
IFBench44.6%34.3%
AA-LCR (Long Context Reasoning)67.0%49.3%
Terminal-Bench Hard48.5%8.3%
τ²-Bench (Telecom)84.8%25.1%
Design Arena (Elo)
Website1,303843
Web apps1,219
Full-stack1,229
Mobile apps1,238
Android native1,216
UI components1,300901
Data viz1,296870
SVG1,251
3D1,303897
Game dev1,301930
Agentic game dev1,215
Code categories1,304876
ASCII art1,273
Specs
Context window1M128K
Max output tokens128K16K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeGPT