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 4.6Gemini 3.5 Flash
Claude Opus 4.6

Anthropic

Gemini 3.5 Flash

Google

Pricing
Input $/1M$5.00$1.50
Output $/1M$25.00$9.00
Blended $/1M (3:1)$10.00$3.38
Cache read $/1M$0.50$0.15
Cache write $/1M$6.25$0.083
Quality indices
Intelligence Index37.850.2
Coding Index70.1
Math Index
Agentic Index37.4
Speed & latency
Output speed (tok/s)54283
Time to first token1.89s11.30s
Time to first answer token1.89s11.30s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%92.2%
Humanity's Last Exam18.6%41.0%
SciCode45.7%53.1%
IFBench44.6%76.3%
AA-LCR (Long Context Reasoning)58.3%69.3%
Terminal-Bench Hard48.5%40.9%
Terminal-Bench 2.178.7%
τ²-Bench (Telecom)84.8%95.3%
τ³-Bench Banking25.4%
Design Arena (Elo)
Website1,3231,283
Web apps1,2611,254
Full-stack1,2791,253
Mobile apps1,2801,250
Android native1,1951,224
UI components1,3361,304
Data viz1,3221,261
SVG1,2741,295
3D1,3351,291
Game dev1,3371,319
Agentic game dev1,190
Godot game dev1,171
HTML slides1,170
PPTX slides1,244
Python→PPTX slides1,247
Agentic slides1,244
Agentic HTML slides1,162
Agentic slides (HTML)1,162
Agentic slides (Python PPTX)1,242
Code categories1,3271,289
ASCII art1,2981,305
Specs
Context window1M1.05M
Max output tokens128K66K
Input modalitiestext, image, filetext, image, video, file, audio
TokenizerClaudeGemini