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 Sonnet 5GPT-5.1
Claude Sonnet 5

Anthropic

GPT-5.1

OpenAI

Pricing
Input $/1M$2.00$1.25
Output $/1M$10.00$10.00
Blended $/1M (3:1)$4.00$3.44
Cache read $/1M$0.20$0.125
Cache write $/1M$2.50
Quality indices
Intelligence Index53.436.9
Coding Index71.549.4
Math Index94
Agentic Index46.721
Speed & latency
Output speed (tok/s)86110
Time to first token93.73s41.75s
Time to first answer token93.73s41.75s
Benchmarks (Artificial Analysis)
MMLU-Pro87.0%
GPQA Diamond91.1%87.3%
Humanity's Last Exam39.6%26.5%
LiveCodeBench86.8%
SciCode53.6%43.3%
AIME 202594.0%
IFBench72.9%
AA-LCR (Long Context Reasoning)70.7%75.0%
Terminal-Bench Hard45.5%
Terminal-Bench 2.180.5%52.4%
τ²-Bench (Telecom)81.9%
τ³-Bench Banking28.2%14.0%
Design Arena (Elo)
Website1,3141,215
Web apps1,3051,075
Full-stack1,292
Mobile apps1,122
Android native1,255
UI components1,3171,209
Data viz1,2811,241
SVG1,2391,196
3D1,3211,120
Game dev1,3451,237
Agentic game dev1,241
Godot game dev1,257
HTML slides1,233
Python→PPTX slides1,252
Code categories1,3121,204
ASCII art1,2301,160
Specs
Context window1M400K
Max output tokens128K128K
Input modalitiestext, image, fileimage, text, file
TokenizerClaudeGPT