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 3 HaikuGPT-5.6 Sol
Claude 3 Haiku

Anthropic

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.25$5.00
Output $/1M$1.25$30.00
Blended $/1M (3:1)$0.50$11.25
Cache read $/1M$0.03$0.50
Cache write $/1M$0.30$6.25
Quality indices
Intelligence Index3.958.9
Coding Index77.4
Math Index
Agentic Index54
Speed & latency
Output speed (tok/s)067
Time to first token0s120.38s
Time to first answer token0s120.38s
Benchmarks (Artificial Analysis)
GPQA Diamond37.4%94.1%
Humanity's Last Exam3.9%47.2%
LiveCodeBench15.4%
SciCode18.6%56.1%
MATH-50039.4%
AIME1.0%
IFBench36.1%72.7%
AA-LCR (Long Context Reasoning)21.0%73.7%
Terminal-Bench Hard0.8%65.9%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)21.1%85.1%
τ³-Bench Banking33.0%
Specs
Context window200K1.05M
Max output tokens4K128K
Input modalitiestext, imagefile, image, text
TokenizerClaudeGPT