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 3.5 (batch)GPT-5.6 Sol
Mistral Medium 3.5 (batch)

Mistral

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.75$2.00
Output $/1M$3.75$10.00
Blended $/1M (3:1)$1.50$4.00
Cache read $/1M$0.20
Cache write $/1M$2.50
Quality indices
Intelligence Index14.247
Coding Index46.977.4
Math Index
Agentic Index750.2
Speed & latency
Output speed (tok/s)15265
Time to first token0.65s64.46s
Time to first answer token13.83s64.46s
Benchmarks (Artificial Analysis)
GPQA Diamond74.8%94.1%
Humanity's Last Exam13.8%49.5%
SciCode40.2%57.1%
IFBench68.8%72.7%
AA-LCR (Long Context Reasoning)69.3%84.0%
Terminal-Bench Hard33.3%65.9%
Terminal-Bench 2.150.6%88.0%
τ²-Bench (Telecom)94.2%85.1%
τ³-Bench Banking15.1%44.3%
Specs
Context window262K1.05M
Max output tokens210K128K
Input modalitiestext, image, filefile, image, text
TokenizerMistralGPT