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 2.5 Pro (batch)
Claude Sonnet 5

Anthropic

Gemini 2.5 Pro (batch)

Google

Pricing
Input $/1M$2.00$0.625
Output $/1M$10.00$5.00
Blended $/1M (3:1)$4.00$1.72
Cache read $/1M$0.20$0.125
Cache write $/1M$2.50
Quality indices
Intelligence Index38.216.1
Coding Index71.533.3
Math Index87.7
Agentic Index43.61.6
Speed & latency
Output speed (tok/s)820
Time to first token118.14s0s
Time to first answer token118.14s0s
Benchmarks (Artificial Analysis)
MMLU-Pro86.2%
GPQA Diamond91.1%84.4%
Humanity's Last Exam41.3%22.5%
LiveCodeBench80.1%
SciCode54.3%46.3%
MATH-50096.7%
AIME88.7%
AIME 202587.7%
IFBench48.7%
AA-LCR (Long Context Reasoning)82.0%69.0%
Terminal-Bench Hard26.5%
Terminal-Bench 2.180.5%28.5%
τ²-Bench (Telecom)54.1%
τ³-Bench Banking37.3%9.7%
Design Arena (Elo)
Website1,2881,179
Web apps1,260
Full-stack1,260
Mobile apps1,249
Android native1,240
UI components1,2991,155
Data viz1,2601,236
SVG1,212
3D1,2891,109
Game dev1,3131,135
Agentic game dev1,227
Godot game dev1,238
HTML slides1,220
Python→PPTX slides1,216
Code categories1,2931,167
ASCII art1,226
Specs
Context window1M1.05M
Max output tokens128K66K
Input modalitiestext, image, filetext, image, file, audio, video
TokenizerClaudeGemini