Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Coding on Codex-Eval
Loading...
94.1
Pass@10
GPT-4
17.556
37.428
57.3
77.172
Jun 7, 2023
Pass@10
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@10
GPT-4
Shots=0-shot
2023.06
94.1
ChatGPT
Shots=0-shot
2023.06
88.4
ShareGPT 65B
Shots=0-shot
2023.06
56.2
TÜLU 65B
Shots=0-shot
2023.06
49.4
TÜLU 30B
Shots=0-shot
2023.06
48
LLaMa 65B
Shots=0-shot
2023.06
46.9
Human mix. 65B
Shots=0-shot
2023.06
44.6
LLaMa 30B
Shots=0-shot
2023.06
42.8
TÜLU-1.1 13B
Shots=0-shot
2023.06
38.9
TÜLU 13B
Shots=0-shot
2023.06
35.9
TÜLU-1.1 7B
Shots=0-shot
2023.06
33.9
LLaMa-2 13B
Shots=0-shot
2023.06
32.5
TÜLU 7B
Shots=0-shot
2023.06
29.1
LLaMa 13B
Shots=0-shot
2023.06
28.6
LLaMa-2 7B
Shots=0-shot
2023.06
26.8
LLaMa 7B
Shots=0-shot
2023.06
20.5
Feedback
Search any
task
Search any
task