← back to paper

Review history

arxiv: 2605.03195 · 3 revisions

Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?

1. 2026-07-12 CONDITIONAL HIGH v1.1.0-grok45 novelty 6.0
   42467 ms 24928 in 3458 out 2026-07-12T17:41:32.698780+00:00
2. 2026-05-08 UNVERDICTED LOW v0.9.0 novelty 4.0
   78698 ms 5601 in 1292 out 2026-05-08T18:05:19.549400+00:00
3. 2026-05-07 UNVERDICTED LOW v0.9.0 novelty 4.0
   32282 ms 5579 in 1094 out 2026-05-07T01:54:56.789913+00:00