Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-context Temporal Reasoning on EventQA
Loading...
0.856
Accuracy (64K)
Qwen3-4B RL finetuned on HanabiRewards
0.83936
0.84368
0.848
0.85232
Jan 26, 2026
Accuracy (64K)
Accuracy (128K)
Accuracy (800K)
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy (64K)
Accuracy (128K)
Accuracy (800K)
Qwen3-4B RL finetuned on HanabiRewards
Backbone=Qwen3-4B, Tra...
2026.01
0.856
0.668
0.436
Qwen3-4B-Instruct-2507
Backbone=Qwen3-4B, Set...
2026.01
0.84
0.626
0.372
Feedback
Search any
task
Search any
task