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.

Claude Opus 4.6Step 3.7 Flash
Claude Opus 4.6

Anthropic

Step 3.7 Flash

Stepfun

Pricing
Input $/1M$5.00$0.20
Output $/1M$25.00$1.15
Blended $/1M (3:1)$10.00$0.438
Cache read $/1M$0.50$0.04
Cache write $/1M$6.25
Quality indices
Intelligence Index37.830.3
Coding Index39.6
Math Index
Agentic Index21.5
Speed & latency
Output speed (tok/s)57401
Time to first token1.85s0.72s
Time to first answer token1.85s5.71s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%80.9%
Humanity's Last Exam18.6%19.9%
SciCode45.7%40.0%
IFBench44.6%67.3%
AA-LCR (Long Context Reasoning)58.3%63.7%
Terminal-Bench Hard48.5%35.6%
Terminal-Bench 2.139.3%
τ²-Bench (Telecom)84.8%98.5%
τ³-Bench Banking11.3%
Design Arena (Elo)
Website1,3231,210
Web apps1,261
Full-stack1,279
Mobile apps1,280
Android native1,195
UI components1,3361,201
Data viz1,3221,200
SVG1,2741,121
3D1,3351,178
Game dev1,3371,200
Code categories1,3271,201
ASCII art1,2981,204
Specs
Context window1M262K
Max output tokens128K256K
Input modalitiestext, image, filetext, image, video
TokenizerClaudeOther