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.

GPT-5.6 SolMiMo-V2.5
GPT-5.6 Sol

OpenAI

MiMo-V2.5

Xiaomi

Pricing
Input $/1M$5.00$0.14
Output $/1M$30.00$0.28
Blended $/1M (3:1)$11.25$0.175
Cache read $/1M$0.50$0.0028
Cache write $/1M$6.25
Quality indices
Intelligence Index58.937.2
Coding Index77.456.8
Math Index
Agentic Index5423.7
Speed & latency
Output speed (tok/s)7063
Time to first token112.90s3.40s
Time to first answer token112.90s34.93s
Benchmarks (Artificial Analysis)
GPQA Diamond94.1%84.9%
Humanity's Last Exam47.2%25.2%
SciCode56.1%43.1%
IFBench72.7%67.1%
AA-LCR (Long Context Reasoning)73.7%62.7%
Terminal-Bench Hard65.9%41.7%
Terminal-Bench 2.188.0%63.7%
τ²-Bench (Telecom)85.1%90.6%
τ³-Bench Banking33.0%6.6%
Design Arena (Elo)
Website1,288
UI components1,294
Data viz1,279
SVG1,218
3D1,273
Game dev1,291
Code categories1,286
ASCII art1,175
Specs
Context window1.05M1.05M
Max output tokens128K131K
Input modalitiesfile, image, texttext, audio, image, video
TokenizerGPTOther