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 Sonnet 5Gemini 3.1 Flash Lite Preview
Claude Sonnet 5

Anthropic

Gemini 3.1 Flash Lite Preview

Google

Pricing
Input $/1M$2.00$0.25
Output $/1M$10.00$1.50
Blended $/1M (3:1)$4.00$0.563
Cache read $/1M$0.20$0.025
Cache write $/1M$2.50$0.083
Quality indices
Intelligence Index53.425
Coding Index71.534.7
Math Index
Agentic Index46.76.2
Speed & latency
Output speed (tok/s)88326
Time to first token93.55s4.89s
Time to first answer token93.55s4.89s
Benchmarks (Artificial Analysis)
GPQA Diamond91.1%82.2%
Humanity's Last Exam39.6%16.2%
SciCode53.6%41.9%
IFBench77.2%
AA-LCR (Long Context Reasoning)70.7%65.3%
Terminal-Bench Hard24.2%
Terminal-Bench 2.180.5%31.1%
τ²-Bench (Telecom)31.3%
τ³-Bench Banking28.2%8.7%
Design Arena (Elo)
Website1,3141,109
Web apps1,305
Full-stack1,292
Android native1,255
UI components1,3171,113
Data viz1,2811,081
SVG1,2391,099
3D1,3211,107
Game dev1,3451,090
Agentic game dev1,241
Godot game dev1,257
HTML slides1,233
Python→PPTX slides1,252
Code categories1,3121,105
ASCII art1,2301,209
Specs
Context window1M1.05M
Max output tokens128K66K
Input modalitiestext, image, filetext, image, video, file, audio
TokenizerClaudeGemini