3 results Clear filters
Ranked by raw score for LiveCodeBench - . Versions are kept separate, and incompatible results are never combined.
Fugu Ultraby Sakana
2026-06-15
sakana/fugu-ultra

Quality-first multi-agent model for hard research, analysis, and competitions

T Reasoning Tools Structured output Weight access not listed
Context
1M
Input
$5/M
Output
$30/M
Fuguby Sakana
2026-06-15
sakana/fugu

Multi-agent model for routing expert agents across complex analytical tasks

T Reasoning Tools Structured output Weight access not listed
Context
1M
Input
-
Output
-
2026-06-04
nvidia/nemotron-3-ultra-550b-a55b

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

T Reasoning Tools Structured output Open weights
Context
1M
Input
$0.5/M
Output
$2.5/M