Add Terminal-Bench evaluation results
Browse files
.eval_results/terminal-bench-2.0.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: harborframework/terminal-bench-2.0
|
| 3 |
+
task_id: terminalbench_2
|
| 4 |
+
value: 20
|
| 5 |
+
date: "2026-06-23"
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/allenai/tmax-4b
|
| 8 |
+
name: Model Card
|
| 9 |
+
notes: "Approximate score (\"roughly 20%\") from TBLite, a lighter/subset harness -- not the full Terminal-Bench 2.0 suite."
|