LiveBench Long Agentic ↗2.0 · 2026-10-25 (dataset 20261025)
8.4%Effort: max · single run
Abacus.AIDiscovered Oct 27, 2026
Smaug-Nemotron-3.5-NVFP4
Measured performance
All leaderboards ↗Benchmark results
LiveBench Reasoning ↗2.0 · 2026-10-25 (dataset 20261025)
75.1%Effort: max · single run
LiveBench Coding ↗2.0 · 2026-10-25 (dataset 20261025)
72.2%Effort: max · single run
LiveBench Browser ↗2.0 · 2026-10-25 (dataset 20261025)
25.6%Effort: max · single run
LiveBench Data Analysis ↗2.0 · 2026-10-25 (dataset 20261025)
65.1%Effort: max · single run
LiveBench Research ↗2.0 · 2026-10-25 (dataset 20261025)
67.8%Effort: max · single run
LiveBench Design ↗2.0 · 2026-10-25 (dataset 20261025)
62.7%Effort: max · single run
Access & cost
0 quotesPrices across providers
No listed provider price
Model specifications
- Developer
- Abacus.AI
- Modality
- Language
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Open weights
- First discovered
- Oct 27, 2026