Skip to content

Models · Text

vikasit-mini

Lightweight assistant. Summaries, chat, and basic reasoning.

Parameters
1.7B
Context window
128K
Best for
Basic reasoning

Benchmarks

GPQA Diamond40.1%
AIME 202448.3%
AIME 202536.8%
LiveCodeBench33.2%
MATH-50093.4%

Thinking mode, no tools where applicable. See full comparisons on the benchmarks page.

Run it

# via Vikasit Inference (OpenAI-compatible)
base_url = "https://api.vikasit.ai"
model = "vikasit-mini"