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 4.7 (batch)GPT-5.6 Terra
Claude Opus 4.7 (batch)

Anthropic

GPT-5.6 Terra

OpenAI

Pricing
Input $/1M$2.50$2.00
Output $/1M$12.50$12.00
Blended $/1M (3:1)$5.00$4.50
Cache read $/1M$0.25$0.20
Cache write $/1M$3.13$2.50
Quality indices
Intelligence Index40.742.1
Coding Index73.676.7
Math Index
Agentic Index38.643.2
Speed & latency
Output speed (tok/s)088
Time to first token0s130.06s
Time to first answer token0s130.06s
Benchmarks (Artificial Analysis)
GPQA Diamond91.4%92.5%
Humanity's Last Exam42.3%42.9%
SciCode55.0%
IFBench58.6%71.2%
AA-LCR (Long Context Reasoning)78.7%83.0%
Terminal-Bench Hard51.5%57.6%
Terminal-Bench 2.183.1%88.0%
τ²-Bench (Telecom)88.6%86.3%
τ³-Bench Banking34.6%40.2%
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT