Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
====================================================================================================
|
| 8 |
+
FINAL SUMMARY
|
| 9 |
+
====================================================================================================
|
| 10 |
+
benchmark primary_metric score accuracy_pct acc_norm_pct extra
|
| 11 |
+
BananaMind Base Bench 1.1 Overall Elo 875.000000 33.428571 NaN weighted_acc=32.52%
|
| 12 |
+
ArithMark 3.0 acc_norm 33.100000 32.900000 33.100000 official AxiomicLabs runner
|
| 13 |
+
ARC Easy acc_norm 37.205387 40.067340 37.205387 lm-eval 0.4.12, zero-shot
|
| 14 |
+
ARC Challenge acc_norm 22.866894 17.918089 22.866894 lm-eval 0.4.12, zero-shot
|
| 15 |
+
HellaSwag acc_norm 28.380801 27.604063 28.380801 lm-eval 0.4.12, zero-shot
|
| 16 |
+
PIQA acc_norm 60.228509 59.793254 60.228509 lm-eval 0.4.12, zero-shot
|
| 17 |
+
|
| 18 |
+
INT Index: 10.603
|