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 (batch)GPT-5.6 Terra
Claude Fable 5 (batch)

Anthropic

GPT-5.6 Terra

OpenAI

Pricing
Input $/1M$5.00$2.00
Output $/1M$25.00$12.00
Blended $/1M (3:1)$10.00$4.50
Cache read $/1M$0.50$0.20
Cache write $/1M$6.25$2.50
Quality indices
Intelligence Index49.642.1
Coding Index76.576.7
Math Index
Agentic Index50.743.2
Speed & latency
Output speed (tok/s)6288
Time to first token52.67s130.06s
Time to first answer token52.67s130.06s
Benchmarks (Artificial Analysis)
GPQA Diamond92.6%92.5%
Humanity's Last Exam55.5%42.9%
SciCode61.0%55.0%
IFBench63.5%71.2%
AA-LCR (Long Context Reasoning)82.3%83.0%
Terminal-Bench Hard62.9%57.6%
Terminal-Bench 2.184.6%88.0%
τ²-Bench (Telecom)98.5%86.3%
τ³-Bench Banking38.1%40.2%
Design Arena (Elo)
Website1,309
Web apps1,274
Full-stack1,286
Mobile apps1,295
Android native1,293
UI components1,333
Data viz1,322
SVG1,329
3D1,347
Game dev1,359
Agentic game dev1,285
Godot game dev1,307
HTML slides1,280
Python→PPTX slides1,294
Agentic HTML slides1,254
Agentic slides (HTML)1,252
Code categories1,325
ASCII art1,343
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT