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-5.1
Claude Opus 4.6

Anthropic

GPT-5.1

OpenAI

Pricing
Input $/1M$5.00$1.25
Output $/1M$25.00$10.00
Blended $/1M (3:1)$10.00$3.44
Cache read $/1M$0.50$0.125
Cache write $/1M$6.25
Quality indices
Intelligence Index37.836.9
Coding Index49.4
Math Index94
Agentic Index21
Speed & latency
Output speed (tok/s)54110
Time to first token1.89s41.75s
Time to first answer token1.89s41.75s
Benchmarks (Artificial Analysis)
MMLU-Pro87.0%
GPQA Diamond84.0%87.3%
Humanity's Last Exam18.6%26.5%
LiveCodeBench86.8%
SciCode45.7%43.3%
AIME 202594.0%
IFBench44.6%72.9%
AA-LCR (Long Context Reasoning)58.3%75.0%
Terminal-Bench Hard48.5%45.5%
Terminal-Bench 2.152.4%
τ²-Bench (Telecom)84.8%81.9%
τ³-Bench Banking14.0%
Design Arena (Elo)
Website1,3231,215
Web apps1,2611,075
Full-stack1,279
Mobile apps1,2801,122
Android native1,195
UI components1,3361,209
Data viz1,3221,241
SVG1,2741,196
3D1,3351,120
Game dev1,3371,237
Code categories1,3271,204
ASCII art1,2981,160
Specs
Context window1M400K
Max output tokens128K128K
Input modalitiestext, image, fileimage, text, file
TokenizerClaudeGPT