deucebucket commited on
Commit
c6379dc
·
verified ·
1 Parent(s): b4f07a6

Add benchmark: MMLU-Redux 58.4%

Browse files
benchmark_results/mmlu_redux_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "benchmark": "mmlu_redux",
3
+ "model": "cerebellum_v2b",
4
+ "accuracy": 58.416666666666664,
5
+ "correct": 1402,
6
+ "total": 2400,
7
+ "elapsed_seconds": 95.17539048194885,
8
+ "timestamp": "2026-04-30 12:47"
9
+ }