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 3.6 Flash
Claude Opus 4.6

Anthropic

Gemini 3.6 Flash

Google

Pricing
Input $/1M$5.00$0.75
Output $/1M$25.00$3.75
Blended $/1M (3:1)$10.00$1.50
Cache read $/1M$0.50$0.075
Cache write $/1M$6.25$0.042
Quality indices
Intelligence Index26.434
Coding Index69.2
Math Index
Agentic Index29
Speed & latency
Output speed (tok/s)0265
Time to first token0s21.43s
Time to first answer token0s21.43s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%92.8%
Humanity's Last Exam19.1%40.8%
SciCode53.4%
IFBench44.6%
AA-LCR (Long Context Reasoning)67.0%80.0%
Terminal-Bench Hard48.5%
Terminal-Bench 2.177.5%
τ²-Bench (Telecom)84.8%
τ³-Bench Banking29.9%
Design Arena (Elo)
Website1,3031,312
Web apps1,2191,211
Full-stack1,2291,188
Mobile apps1,2381,228
Android native1,2161,213
UI components1,3001,318
Data viz1,2961,311
SVG1,251
3D1,3031,302
Game dev1,3011,286
Agentic game dev1,2151,180
HTML slides1,152
Python→PPTX slides1,146
Code categories1,3041,305
ASCII art1,2731,304
Specs
Context window1M1.05M
Max output tokens128K66K
Input modalitiestext, image, filetext, image, video, file, audio
TokenizerClaudeGemini