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 Medium 3.1GPT-5.6 Sol
Mistral Medium 3.1

Mistral

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.40$5.00
Output $/1M$2.00$30.00
Blended $/1M (3:1)$0.80$11.25
Cache read $/1M$0.04$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index14.758.9
Coding Index20.577.4
Math Index38.3
Agentic Index6.254
Speed & latency
Output speed (tok/s)8467
Time to first token0.51s120.38s
Time to first answer token0.51s120.38s
Benchmarks (Artificial Analysis)
MMLU-Pro68.3%
GPQA Diamond58.8%94.1%
Humanity's Last Exam4.4%47.2%
LiveCodeBench40.6%
SciCode33.8%56.1%
AIME 202538.3%
IFBench39.8%72.7%
AA-LCR (Long Context Reasoning)19.7%73.7%
Terminal-Bench Hard10.6%65.9%
Terminal-Bench 2.113.9%88.0%
τ²-Bench (Telecom)40.6%85.1%
τ³-Bench Banking8.5%33.0%
Design Arena (Elo)
Website1,160
UI components1,140
Data viz1,184
SVG1,039
3D1,140
Game dev1,132
Code categories1,154
ASCII art1,040
Specs
Context window131K1.05M
Max output tokens128K
Input modalitiestext, image, filefile, image, text
TokenizerMistralGPT