Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Error Prediction on AmbigQA (val)

69.8PRR

Spectrum-Qwen3-14B

-1.33617.13235.654.068Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
69.8-
2026.06
69.6-
2026.06
69.6-
2026.06
69.5-
2026.06
68.8-
2026.06
68.5-
2026.06
68.3-
2026.06
68.1-
2026.06
65.1-
2026.06
65.1-
2026.06
64.4-
2026.06
63.3-
2026.06
63.2-
2026.06
62.7-
2026.06
62-
2026.06
61.6-
2026.06
61.4-
2026.06
60.7-
2026.06
60.5-
2026.06
60.2-
2026.06
59.3-
2026.06
58.4-
2026.06
58-
2026.06
58-
2026.06
57.9-
2026.06
57.5-
2026.06
57.5-
2026.06
57.3-
2026.06
57.1-
2026.06
57.1-
2026.06
56.5-
2026.06
56.4-
2026.06
56.2-
2026.06
56.2-
2026.06
56-
2026.06
56-
2026.06
55.6-
2026.06
55.5-
2026.06
55.5-
2026.06
55.3-
2026.06
55.3-
2026.06
54.5-
2026.06
54.3-
2026.06
54.3-
2026.06
53.9-
2026.06
53.8-
2026.06
53.7-
2026.06
53.7-
2026.06
53.6-
2026.06
52.8-
2026.06
52.6-
2026.06
52.6-
2026.06
52.5-
2026.06
52.4-
2026.06
52-
2026.06
52-
2026.06
51.3-
2026.06
51.2-
2026.06
50.8-
2026.06
50.4-
2026.06
49.2-
2026.06
48.3-
2026.06
48.3-
2026.06
47.8-
2026.06
47.1-
2026.06
46.2-
2026.06
46.1-
2026.06
46-
2026.06
45.7-
2026.06
45-
2026.06
44.6-
2026.06
43.2-
2026.06
42.1-
2026.06
39.2-
2026.06
19.9-
2026.06
18.9-
2026.06
18.9-
2026.06
18.2-
2026.06
18.1-
2026.06
7.8-
2026.06
7.8-
2026.06
7.8-
2026.06
7.8-
2026.06
5.8-
2026.06
5.8-
2026.06
5.8-
2026.06
5.8-
2026.06
3-
2026.06
1.4-
2026.06
1.4-
2026.06
-79.9
2026.06
-79.8
2026.06
-79.9
2026.06
-79.7
2026.06
-79.7
2026.06
-76.8
2026.06
-77.1
2026.06
-75.2
2026.06
-75.6
2026.06
-57.8
Showing 100 of 107 rows