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.

GPT-5.6 SolGLM 5.2 (free)
GPT-5.6 Sol

OpenAI

GLM 5.2 (free)

Z.ai

Pricing
Input $/1M$2.00Free
Output $/1M$10.00Free
Blended $/1M (3:1)$4.00Free
Cache read $/1M$0.20
Cache write $/1M$2.50
Quality indices
Intelligence Index4733.7
Coding Index77.468.8
Math Index
Agentic Index50.238.4
Speed & latency
Output speed (tok/s)65
Time to first token64.46s
Time to first answer token64.46s
Benchmarks (Artificial Analysis)
GPQA Diamond94.1%
Humanity's Last Exam49.5%
SciCode57.1%
IFBench72.7%
AA-LCR (Long Context Reasoning)84.0%
Terminal-Bench Hard65.9%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%
τ³-Bench Banking44.3%
Design Arena (Elo)
Website1,304
Web apps1,236
Full-stack1,251
Mobile apps1,190
Android native1,189
UI components1,308
Data viz1,310
SVG1,246
3D1,320
Game dev1,296
Agentic game dev1,205
Godot game dev1,142
HTML slides1,178
Python→PPTX slides1,194
Code categories1,308
ASCII art1,227
Specs
Context window1.05M33K
Max output tokens128K29K
Input modalitiesfile, image, texttext
TokenizerGPTOther