Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Writing Evaluation on HelloBench-G
Loading...
62.89
Score
Gemini-2.5-pro
-94.5036
-53.6418
-12.78
28.0818
Jun 24, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Gemini-2.5-pro
2026.06
62.89
MiniMax-M2.5
2026.06
59.33
OPERA
Backbone=Llama3.1-8B
2026.06
49.83
OPERA
Backbone=Qwen3-8B
2026.06
49.79
Qwen3-8B-SFT
Mode=SFT
2026.06
41.96
GPT-4o-0513
2026.06
38.02
Llama3.1-8B-SFT
Mode=SFT
2026.06
37.53
Qwen3-8B
2026.06
37.12
DeepWriter-8B
2026.06
0.25
Llama3.1-8B
2026.06
-26.07
LongWriter-Zero-32B
2026.06
-55.48
LongWriter-8B
2026.06
-88.45
Feedback
Search any
task
Search any
task