Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
2048 Game on 2048 3x3 grid variant
Loading...
1,184
Score
GPT-5
66.312
356.481
646.65
936.819
Feb 5, 2026
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
GPT-5
2026.02
1,184
Doubao-Seed-1.8
2026.02
545.3
UITARS-1.5
2026.02
466.7
Base Model + GLAD + MC-Critic
Backbone=Qwen3-4B-Inst...
2026.02
464.4
Base Model + GLAD
Backbone=Qwen3-4B-Inst...
2026.02
429.2
Doubao-Seed-1.6
2026.02
300
Qwen3-235B-A22B-Instruct
2026.02
274.7
Qwen3-30B-A3B-Instruct
2026.02
230.7
Qwen3-4B-Instruct (Base Model)
2026.02
187.3
Claude-4.5-Sonnet
2026.02
109.3
Feedback
Search any
task
Search any
task