Spaces:
Running
Running
fix: rescale gemini2 flash-thinking u-math scores
Browse files- data/u_math_eval_results.json +21 -21
data/u_math_eval_results.json
CHANGED
@@ -3,39 +3,39 @@
|
|
3 |
"model_name": "gemini-2.0-flash-thinking-exp-01-21",
|
4 |
"judge_model_name": "gpt-4o-2024-08-06",
|
5 |
"u_math": [
|
6 |
-
|
7 |
-
|
8 |
-
0
|
9 |
],
|
10 |
"multivariable_calculus": [
|
11 |
-
|
12 |
-
0
|
13 |
-
0
|
14 |
],
|
15 |
"integral_calc": [
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
],
|
20 |
"sequences_series": [
|
21 |
-
|
22 |
-
0
|
23 |
-
0
|
24 |
],
|
25 |
"differential_calc": [
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
],
|
30 |
"algebra": [
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
],
|
35 |
"precalculus_review": [
|
36 |
-
|
37 |
-
|
38 |
-
0
|
39 |
]
|
40 |
},
|
41 |
{
|
|
|
3 |
"model_name": "gemini-2.0-flash-thinking-exp-01-21",
|
4 |
"judge_model_name": "gpt-4o-2024-08-06",
|
5 |
"u_math": [
|
6 |
+
73.64,
|
7 |
+
77.78,
|
8 |
+
55.0
|
9 |
],
|
10 |
"multivariable_calculus": [
|
11 |
+
74.16,
|
12 |
+
74.0,
|
13 |
+
75.0
|
14 |
],
|
15 |
"integral_calc": [
|
16 |
+
55.29,
|
17 |
+
54.67,
|
18 |
+
56.9
|
19 |
],
|
20 |
"sequences_series": [
|
21 |
+
78.57,
|
22 |
+
80.0,
|
23 |
+
25.0
|
24 |
],
|
25 |
"differential_calc": [
|
26 |
+
62.27,
|
27 |
+
69.33,
|
28 |
+
47.14
|
29 |
],
|
30 |
"algebra": [
|
31 |
+
87.22,
|
32 |
+
93.33,
|
33 |
+
56.67
|
34 |
],
|
35 |
"precalculus_review": [
|
36 |
+
92.5,
|
37 |
+
95.33,
|
38 |
+
50.0
|
39 |
]
|
40 |
},
|
41 |
{
|