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.

Mistral Small 3GPT-5.6 Sol
Mistral Small 3

Mistral

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.05$5.00
Output $/1M$0.08$30.00
Blended $/1M (3:1)$0.057$11.25
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index6.958.9
Coding Index77.4
Math Index4.3
Agentic Index54
Speed & latency
Output speed (tok/s)16667
Time to first token0.53s120.38s
Time to first answer token0.53s120.38s
Benchmarks (Artificial Analysis)
MMLU-Pro65.2%
GPQA Diamond46.2%94.1%
Humanity's Last Exam4.1%47.2%
LiveCodeBench25.2%
SciCode23.6%56.1%
MATH-50071.5%
AIME8.0%
AIME 20254.3%
IFBench26.4%72.7%
AA-LCR (Long Context Reasoning)0.0%73.7%
Terminal-Bench Hard65.9%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)19.6%85.1%
τ³-Bench Banking33.0%
Specs
Context window33K1.05M
Max output tokens16K128K
Input modalitiestextfile, image, text
TokenizerMistralGPT