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 3.5 Flash
GPT-5.6 Sol

OpenAI

Step 3.5 Flash

Stepfun

Pricing
Input $/1M$5.00$0.10
Output $/1M$30.00$0.30
Blended $/1M (3:1)$11.25$0.15
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index58.926
Coding Index77.4
Math Index
Agentic Index54
Speed & latency
Output speed (tok/s)70298
Time to first token112.90s0.74s
Time to first answer token112.90s7.45s
Benchmarks (Artificial Analysis)
GPQA Diamond94.1%82.6%
Humanity's Last Exam47.2%22.6%
SciCode56.1%38.5%
IFBench72.7%66.5%
AA-LCR (Long Context Reasoning)73.7%54.3%
Terminal-Bench Hard65.9%32.6%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%87.4%
τ³-Bench Banking33.0%
Specs
Context window1.05M262K
Max output tokens128K66K
Input modalitiesfile, image, texttext
TokenizerGPTOther