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 4.5 (batch)GPT-4.1
Claude Opus 4.5 (batch)

Anthropic

GPT-4.1

OpenAI

Pricing
Input $/1M$2.50$2.00
Output $/1M$12.50$8.00
Blended $/1M (3:1)$5.00$3.50
Cache read $/1M$0.25$0.50
Cache write $/1M$3.13
Quality indices
Intelligence Index23.712.7
Coding Index
Math Index62.734.7
Agentic Index
Speed & latency
Output speed (tok/s)00
Time to first token0s0s
Time to first answer token0s0s
Benchmarks (Artificial Analysis)
MMLU-Pro88.9%80.6%
GPQA Diamond81.0%66.6%
Humanity's Last Exam13.2%4.2%
LiveCodeBench73.8%45.7%
MATH-50091.3%
AIME43.7%
AIME 202562.7%34.7%
IFBench43.0%43.0%
AA-LCR (Long Context Reasoning)70.7%68.3%
Terminal-Bench Hard40.9%13.6%
τ²-Bench (Telecom)86.3%47.1%
Design Arena (Elo)
Website1,2591,051
Web apps1,174
Full-stack1,166
Mobile apps1,218
Android native1,190
UI components1,2541,016
Data viz1,2581,117
SVG1,204
3D1,242878
Game dev1,2521,103
Code categories1,2571,041
ASCII art1,208
Specs
Context window200K1.05M
Max output tokens64K33K
Input modalitiesfile, image, textimage, text, file
TokenizerClaudeGPT