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 Haiku 4.5GPT-5.1-Codex-Mini
Claude Haiku 4.5

Anthropic

GPT-5.1-Codex-Mini

OpenAI

Pricing
Input $/1M$1.00$0.25
Output $/1M$5.00$2.00
Blended $/1M (3:1)$2.00$0.688
Cache read $/1M$0.10$0.025
Cache write $/1M$1.25
Quality indices
Intelligence Index29.630.6
Coding Index43.9
Math Index91.7
Agentic Index16.4
Speed & latency
Output speed (tok/s)212
Time to first token5.47s
Time to first answer token5.47s
Benchmarks (Artificial Analysis)
MMLU-Pro82.0%
GPQA Diamond81.3%
Humanity's Last Exam16.9%
LiveCodeBench83.6%
SciCode42.6%
AIME 202591.7%
IFBench67.9%
AA-LCR (Long Context Reasoning)62.7%
Terminal-Bench Hard33.3%
τ²-Bench (Telecom)62.9%
Design Arena (Elo)
Website1,1491,138
UI components1,1421,122
Data viz1,1601,133
SVG1,0721,024
3D1,1311,048
Game dev1,1551,151
Code categories1,1481,127
ASCII art1,1821,147
Specs
Context window200K400K
Max output tokens64K100K
Input modalitiestext, image, fileimage, text
TokenizerClaudeGPT