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 Fable 5.1 (batch)GPT-5.6 Sol
Claude Fable 5.1 (batch)

Anthropic

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$5.00$2.00
Output $/1M$25.00$10.00
Blended $/1M (3:1)$10.00$4.00
Cache read $/1M$0.125$0.20
Cache write $/1M$6.25$2.50
Quality indices
Intelligence Index53.447
Coding Index81.677.4
Math Index
Agentic Index57.950.2
Speed & latency
Output speed (tok/s)7365
Time to first token153.32s64.46s
Time to first answer token153.32s64.46s
Benchmarks (Artificial Analysis)
GPQA Diamond93.7%94.1%
Humanity's Last Exam59.1%49.5%
SciCode63.1%57.1%
IFBench72.7%
AA-LCR (Long Context Reasoning)85.3%84.0%
Terminal-Bench Hard65.9%
Terminal-Bench 2.191.4%88.0%
τ²-Bench (Telecom)85.1%
τ³-Bench Banking47.2%44.3%
Design Arena (Elo)
Website1,323
Web apps1,336
Full-stack1,336
UI components1,336
Data viz1,369
SVG1,347
3D1,425
Game dev1,404
Python→PPTX slides1,328
Code categories1,346
ASCII art1,330
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT