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 3.8 Flash (batch)
Claude Opus 4.6

Anthropic

Gemini 3.8 Flash (batch)

Google

Pricing
Input $/1M$5.00$0.375
Output $/1M$25.00$1.88
Blended $/1M (3:1)$10.00$0.75
Cache read $/1M$0.50$0.037
Cache write $/1M$6.25$0.042
Quality indices
Intelligence Index26.440.9
Coding Index76.3
Math Index
Agentic Index40.2
Speed & latency
Output speed (tok/s)0327
Time to first token0s12.22s
Time to first answer token0s12.22s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%95.3%
Humanity's Last Exam19.1%47.8%
SciCode56.6%
IFBench44.6%
AA-LCR (Long Context Reasoning)67.0%81.3%
Terminal-Bench Hard48.5%
Terminal-Bench 2.187.6%
τ²-Bench (Telecom)84.8%
τ³-Bench Banking44.9%
Design Arena (Elo)
Website1,3031,315
Web apps1,2191,256
Full-stack1,2291,250
Mobile apps1,2381,259
Android native1,216
UI components1,3001,338
Data viz1,2961,264
SVG1,251
3D1,3031,324
Game dev1,3011,340
Agentic game dev1,215
Python→PPTX slides1,176
Code categories1,3041,323
ASCII art1,273
Specs
Context window1M1.05M
Max output tokens128K66K
Input modalitiestext, image, filetext, image, video, file, audio
TokenizerClaudeGemini