Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Learner Simulation on Mistakes
Loading...
58
Accuracy
GPT-5-nano
45.52
48.76
52
55.24
May 19, 2026
Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5-nano
2026.05
58
GRPO
Backbone=Qwen3-VL-8B-I...
2026.05
58
GPT-5.4
2026.05
57
DITTO
Backbone=Qwen3-VL-8B-I...
2026.05
56
HumanLM-8B
2026.05
52
Qwen3-VL-8B-Instruct
Role=Base
2026.05
46
Feedback
Search any
task
Search any
task