Models · Text
vikasit-reasoner-1t
Trillion-scale reasoning MoE. Deep multi-step reasoning, long-horizon agent tasks.
Parameters
1T (63B active)
Context window
262K
Best for
Complex reasoning
Benchmarks
MMLU-Pro85.0%
GPQA Diamond81.0%
AIME 202491.4%
AIME 202587.5%
LiveCodeBench73.3%
SWE-bench Verified57.6%
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-reasoner-1t"