Add Terminal-Bench 2.0 evaluation results
#2
by nielsr HF Staff - opened
.eval_results/terminal_bench_2.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: harborframework/terminal-bench-2.0
|
| 3 |
+
task_id: terminalbench_2
|
| 4 |
+
value: 27.4
|
| 5 |
+
source:
|
| 6 |
+
url: https://arxiv.org/pdf/2602.21193
|
| 7 |
+
name: Nemotron-Terminal-32B technical report
|
| 8 |
+
user: nielsr
|
| 9 |
+
notes: "agent: Terminus 2"
|