Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended cultural on BLEnD
Loading...
22.1
chrF
end-to-end
6.5416
10.5808
14.62
18.6592
Jun 25, 2026
chrF
Updated 29d ago
Evaluation Results
Method
Method
Links
chrF
end-to-end
Model=GPT-4o-mini
2026.06
22.1
standard cascade
Model=GPT-4o-mini
2026.06
17.26
context-aware cascade
Model=GPT-4o-mini
2026.06
17.26
context-aware cascade
Model=Llama-3.1-8B-Ins...
2026.06
12.14
end-to-end
Model=Llama-3.1-8B-Ins...
2026.06
11.91
standard cascade
Model=Llama-3.1-8B-Ins...
2026.06
9.47
context-aware cascade
Model=Mistral-7B-Instr...
2026.06
9.05
standard cascade
Model=Mistral-7B-Instr...
2026.06
8.27
end-to-end
Model=Mistral-7B-Instr...
2026.06
7.14
Feedback
Search any
task
Search any
task