Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Code Reasoning on LiveCodeBench

87.4Accuracy

Gemini-3.0

-3.49620.10243.767.298Dec 1, 2025Dec 13, 2025Dec 26, 2025Jan 8, 2026Jan 21, 2026Feb 3, 2026Feb 16, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
87.4---13,000--
2026.02
85---18,000--
2026.02
83.3---16,000--
2026.02
82.6---25,000--
2026.02
59.5--1---
2026.02
53.53,9880.8----
2026.02
52.32,8730.85----
2026.02
49.69,0950----
2026.01
48.38----70.63-
2026.02
42.6--1.32---
2026.02
40.5--1.25---
2026.02
40.1--1.46---
2026.01
34.95----60.78-9.85
2026.02
34.62---5,587.4--
2026.02
34.62---4,834.88--
2026.02
30.77---6,723.94--
2026.02
30.77---6,103.94--
2026.02
30.47,5670.9----
2026.01
29.1----58.28-12.35
2026.02
28.69,0770.55----
2026.02
25.310,8090----
2026.02
25---5,117.71--
2026.02
23.3--1.15---
2026.02
22.6--1.1---
2026.02
21.9--1.11---
2026.02
21.15---6,433.59--
2026.02
19.25---6,568.69--
2025.12
17.3------
2026.01
16.04----48.72-
2025.12
15.9------
2026.02
15.38---7,055.57--
2025.12
15.3------
2026.01
12.94----41.1-
2026.02
12.9--2.05---
2026.02
10.4--2.64---
2026.01
10.07----41.31-7.41
2026.02
7.5--1.6---
2026.02
7.2--1.42---
2026.02
6.8--1.73---
2026.01
6.72----38.39-10.33
2026.02
4.7--2.83---
2026.02
4.3--2.86---
2026.01
1.87----17.34-23.76
2026.01
1.37----21.44-19.66
2026.01
0----4.84-36.26
2026.01
0----2.11-46.61