diff --git a/.eval_results/swe_bench_verified.yaml b/.eval_results/swe_bench_verified.yaml new file mode 100644 index 0000000..a7c48b1 --- /dev/null +++ b/.eval_results/swe_bench_verified.yaml @@ -0,0 +1,9 @@ +- dataset: + id: SWE-bench/SWE-bench_Verified + task_id: swe_bench_%_resolved + value: 75.80 + source: + url: https://www.swebench.com/ + name: SWE-Bench official evaluation + user: nielsr + notes: high reasoning \ No newline at end of file