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 SolStep 3.7 Flash
GPT-5.6 Sol

OpenAI

Step 3.7 Flash

Stepfun

Pricing
Input $/1M$5.00$0.20
Output $/1M$30.00$1.15
Blended $/1M (3:1)$11.25$0.438
Cache read $/1M$0.50$0.04
Cache write $/1M$6.25
Quality indices
Intelligence Index58.930.3
Coding Index77.439.6
Math Index
Agentic Index5421.5
Speed & latency
Output speed (tok/s)70401
Time to first token112.90s0.72s
Time to first answer token112.90s5.71s
Benchmarks (Artificial Analysis)
GPQA Diamond94.1%80.9%
Humanity's Last Exam47.2%19.9%
SciCode56.1%40.0%
IFBench72.7%67.3%
AA-LCR (Long Context Reasoning)73.7%63.7%
Terminal-Bench Hard65.9%35.6%
Terminal-Bench 2.188.0%39.3%
τ²-Bench (Telecom)85.1%98.5%
τ³-Bench Banking33.0%11.3%
Design Arena (Elo)
Website1,210
UI components1,201
Data viz1,200
SVG1,121
3D1,178
Game dev1,200
Code categories1,201
ASCII art1,204
Specs
Context window1.05M262K
Max output tokens128K256K
Input modalitiesfile, image, texttext, image, video
TokenizerGPTOther