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 Mini
Claude Opus 4.5 (batch)

Anthropic

GPT-4.1 Mini

OpenAI

Pricing
Input $/1M$2.50$0.40
Output $/1M$12.50$1.60
Blended $/1M (3:1)$5.00$0.70
Cache read $/1M$0.25$0.10
Cache write $/1M$3.13
Quality indices
Intelligence Index23.710.2
Coding Index20.2
Math Index62.746.3
Agentic Index
Speed & latency
Output speed (tok/s)00
Time to first token0s0s
Time to first answer token0s0s
Benchmarks (Artificial Analysis)
MMLU-Pro88.9%78.1%
GPQA Diamond81.0%66.4%
Humanity's Last Exam13.2%5.0%
LiveCodeBench73.8%48.3%
MATH-50092.5%
AIME43.0%
AIME 202562.7%46.3%
IFBench43.0%38.3%
AA-LCR (Long Context Reasoning)70.7%44.0%
Terminal-Bench Hard40.9%7.6%
Terminal-Bench 2.110.1%
τ²-Bench (Telecom)86.3%52.9%
τ³-Bench Banking5.4%
Design Arena (Elo)
Website1,2591,010
Web apps1,174
Full-stack1,166
Mobile apps1,218
Android native1,190
UI components1,254976
Data viz1,2581,047
SVG1,204
3D1,242865
Game dev1,2521,094
Code categories1,2571,009
ASCII art1,208
Specs
Context window200K1.05M
Max output tokens64K33K
Input modalitiesfile, image, textimage, text, file
TokenizerClaudeGPT