RadixArk/GLM-5.3-NVFP4 · Add Terminal-Bench 2.1 and DeepSWE scores to model card

Add Terminal-Bench 2.1 and DeepSWE scores to model card

#7

by JustinTong - opened 9 days ago

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

RadixArk org 9 days ago

Agentic benchmark results for this checkpoint: Terminal-Bench 2.1 (terminus-2) and DeepSWE (mini-swe-agent), with sampling parameters.

Add Terminal-Bench 2.1 and DeepSWE scores to model card775335f5

Align Terminal-Bench denominator to full 89-task setd2df1d2e

Make Evaluation section consistent across benchmarksb4057c06

JustinTong changed pull request status to merged 9 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment