Add Terminal-Bench evaluation result (33.4%)
Browse files
.eval_results/terminal_bench.yaml
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: harborframework/terminal-bench-2.0
|
| 3 |
+
task_id: terminal_bench
|
| 4 |
+
value: 33.4
|
| 5 |
+
date: '2026-01-28'
|
| 6 |
+
source:
|
| 7 |
+
url: https://www.tbench.ai/leaderboard/terminal-bench/2.0
|
| 8 |
+
name: Terminal-Bench Leaderboard
|
| 9 |
+
user: burtenshaw
|
| 10 |
+
notes: "agent: Terminus 2"
|
| 11 |
+
|