Add Terminal-Bench evaluation results
#10
by nielsr HF Staff - opened
.eval_results/terminal-bench-science.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: harborframework/terminal-bench-science
|
| 3 |
+
task_id: terminalbenchscience_0_1
|
| 4 |
+
value: 2.4
|
| 5 |
+
source:
|
| 6 |
+
url: https://artificialanalysis.ai/evaluations/terminal-bench-science
|
| 7 |
+
name: "Artificial Analysis Terminal-Bench-Science leaderboard"
|
| 8 |
+
user: ArtificialAnalysis
|
| 9 |
+
notes: "Step 5 Preview; mini-swe-agent harness, pass@1 averaged over three repeats."
|