Add community evaluation results for GPQA, MMLU-PRO, SWE-BENCH_VERIFIED

#4
by nielsr HF Staff - opened
.eval_results/gpqa.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: Idavidrein/gpqa
3
+ task_id: diamond
4
+ value: 76.3
5
+ source:
6
+ url: https://huggingface.co/arcee-ai/Trinity-Large-Thinking
7
+ name: Model Card
.eval_results/mmlu-pro.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: TIGER-Lab/MMLU-Pro
3
+ task_id: mmlu_pro
4
+ value: 83.4
5
+ source:
6
+ url: https://huggingface.co/arcee-ai/Trinity-Large-Thinking
7
+ name: Model Card
.eval_results/swe-bench_verified.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: SWE-bench/SWE-bench_Verified
3
+ task_id: swe_bench_%_resolved
4
+ value: 63.2
5
+ source:
6
+ url: https://huggingface.co/arcee-ai/Trinity-Large-Thinking
7
+ name: Model Card