Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Inference on XNLI French
Loading...
59.1
Accuracy
Qwen2.5
32.268
39.234
46.2
53.166
Dec 25, 2025
Jan 13, 2026
Feb 2, 2026
Feb 22, 2026
Mar 13, 2026
Apr 2, 2026
Apr 22, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5
Zero-shot=true, Chat T...
2025.12
59.1
Gamayun
Zero-shot=true, Chat T...
2025.12
57.9
Qwen3
Zero-shot=true, Chat T...
2025.12
52.7
HQ seed (LLM Training)
Filtering Strategy=HQ...
2026.04
49.04
Q3 negatives
Filtering Strategy=Q3...
2026.04
48.76
HQ
Filtering Strategy=HQ
2026.04
48.55
HQ Romance (No Fra)
Filtering Strategy=HQ...
2026.04
48.27
HQ seed
Filtering Strategy=HQ...
2026.04
48.23
ML
Filtering Strategy=ML
2026.04
48.07
ML (15%)
Filtering Strategy=ML...
2026.04
48.07
Nordic
Filtering Strategy=Nordic
2026.04
47.83
ML (Q3)
Filtering Strategy=ML...
2026.04
47.67
MKC-e
Filtering Strategy=MKC-e
2026.04
47.35
No Filtering
Filtering Strategy=No...
2026.04
47.07
HQ all
Filtering Strategy=HQ all
2026.04
46.95
EuroLM
Zero-shot=true, Chat T...
2025.12
33.4
Gemma3
Zero-shot=true, Chat T...
2025.12
33.3
Llama3.2
Zero-shot=true, Chat T...
2025.12
33.3
Feedback
Search any
task
Search any
task