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-5.2 (batch)
Claude Opus 4.6

Anthropic

GPT-5.2 (batch)

OpenAI

Pricing
Input $/1M$5.00$0.875
Output $/1M$25.00$7.00
Blended $/1M (3:1)$10.00$2.41
Cache read $/1M$0.50$0.087
Cache write $/1M$6.25
Quality indices
Intelligence Index26.430.4
Coding Index
Math Index99
Agentic Index
Speed & latency
Output speed (tok/s)00
Time to first token0s0s
Time to first answer token0s0s
Benchmarks (Artificial Analysis)
MMLU-Pro87.4%
GPQA Diamond84.0%90.3%
Humanity's Last Exam19.1%37.7%
LiveCodeBench88.9%
AIME 202599.0%
IFBench44.6%75.4%
AA-LCR (Long Context Reasoning)67.0%82.7%
Terminal-Bench Hard48.5%47.0%
τ²-Bench (Telecom)84.8%84.8%
Design Arena (Elo)
Website1,3031,207
Web apps1,2191,101
Full-stack1,2291,052
Mobile apps1,2381,123
Android native1,2161,073
UI components1,3001,206
Data viz1,2961,216
SVG1,2511,162
3D1,3031,108
Game dev1,3011,219
Agentic game dev1,215
Godot game dev1,142
Code categories1,3041,185
ASCII art1,2731,171
Specs
Context window1M400K
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT