Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-form text generation on LongBench Write-en 1.0 (test)
Loading...
91.8
Sq
GPT-4o
51.968
62.309
72.65
82.991
Feb 4, 2025
Sq
Updated 4d ago
Evaluation Results
Method
Method
Links
Sq
GPT-4o
2025.02
91.8
GPT-4o mini
2025.02
90.3
LongWriter-Qwen + LongDPO
Backbone=Qwen, Optimiz...
2025.02
88.6
Mistral-Large-Instruct
2025.02
88.3
LongWriter-Llama + LongDPO
Backbone=Llama, Optimi...
2025.02
88.2
Claude 3.5 Sonnet
2025.02
87.7
GPT-4 Turbo
2025.02
86.6
GLM-4-9B-chat
2025.02
85.5
LongWriter-Llama
Backbone=Llama
2025.02
82.2
Llama-3.1-70B-Instruct
Parameters=70B
2025.02
80.3
Llama-3.1-8B-Instruct
Parameters=8B
2025.02
70.6
Suri-I-ORPO
2025.02
53.5
Feedback
Search any
task
Search any
task