Add evaluation results from GPT-OSS paper
Browse files
.eval_results/swe_bench_verified_low.yaml
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: SWE-bench/SWE-bench_Verified
|
| 3 |
+
task_id: swe_bench_%_resolved
|
| 4 |
+
value: 37.4
|
| 5 |
+
date: '2025-08-05'
|
| 6 |
+
source:
|
| 7 |
+
url: https://arxiv.org/abs/2508.10925
|
| 8 |
+
name: GPT-OSS Model Card
|
| 9 |
+
user: SaylorTwift
|
| 10 |
+
notes: "Reasoning: low"
|