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 4.6GLM 5.2 (free)
Claude Opus 4.6

Anthropic

GLM 5.2 (free)

Z.ai

Pricing
Input $/1M$5.00Free
Output $/1M$25.00Free
Blended $/1M (3:1)$10.00Free
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index26.433.7
Coding Index68.8
Math Index
Agentic Index38.4
Speed & latency
Output speed (tok/s)0
Time to first token0s
Time to first answer token0s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%
Humanity's Last Exam19.1%
IFBench44.6%
AA-LCR (Long Context Reasoning)67.0%
Terminal-Bench Hard48.5%
τ²-Bench (Telecom)84.8%
Design Arena (Elo)
Website1,3031,304
Web apps1,2191,236
Full-stack1,2291,251
Mobile apps1,2381,190
Android native1,2161,189
UI components1,3001,308
Data viz1,2961,310
SVG1,2511,246
3D1,3031,320
Game dev1,3011,296
Agentic game dev1,2151,205
Godot game dev1,142
HTML slides1,178
Python→PPTX slides1,194
Code categories1,3041,308
ASCII art1,2731,227
Specs
Context window1M33K
Max output tokens128K29K
Input modalitiestext, image, filetext
TokenizerClaudeOther