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.

Gemini 3.6 Flashgpt-oss-20b (free)
Gemini 3.6 Flash

Google

gpt-oss-20b (free)

OpenAI

Pricing
Input $/1M$1.50Free
Output $/1M$7.50Free
Blended $/1M (3:1)$3.00Free
Cache read $/1M$0.15
Cache write $/1M$0.083
Quality indices
Intelligence Index50.114.9
Coding Index69.220.7
Math Index89.3
Agentic Index38.73.1
Speed & latency
Output speed (tok/s)311243
Time to first token12.80s0.39s
Time to first answer token12.80s8.61s
Benchmarks (Artificial Analysis)
MMLU-Pro74.8%
GPQA Diamond92.8%68.8%
Humanity's Last Exam38.3%9.8%
LiveCodeBench77.7%
SciCode52.7%34.4%
AIME 202589.3%
IFBench65.1%
AA-LCR (Long Context Reasoning)69.7%30.7%
Terminal-Bench Hard10.6%
Terminal-Bench 2.177.5%13.9%
τ²-Bench (Telecom)60.2%
τ³-Bench Banking24.5%7.0%
Design Arena (Elo)
Website1,332880
Data viz971
Specs
Context window1.05M131K
Max output tokens66K33K
Input modalitiestext, image, video, file, audiotext
TokenizerGeminiGPT