paper
-with-
me
Papers
Browse State-of-the-Art
Datasets
Methods
AI Agents
Trends
Digest
🌙
Code Completion
벤치마크
Code Completion on
SAFIM
15개 결과 ·
⬇ CSV
·
JSON
Average
22.94
34.46
45.98
57.49
69.01
2024-03
2026-09
deepseek-coder-33b-base — 69.01 (2024-03-07)
deepseek-coder-6.7b-base — 63.4 (2024-03-07)
starcoderbase — 55.54 (2024-03-07)
gpt-4-1106-preview — 53.28 (2024-03-07)
CodeLlama-13b-hf — 52.78 (2024-03-07)
deepseek-coder-1.3b-base — 52.63 (2024-03-07)
CodeLlama-34b-hf — 49.66 (2024-03-07)
CodeLlama-7b-hf — 45.0 (2024-03-07)
gpt-3.5-turbo-0301 — 40.86 (2024-03-07)
incoder-6B — 33.79 (2024-03-07)
codegen-16B-multi — 30.99 (2024-03-07)
codegen-2B-multi — 29.55 (2024-03-07)
incoder-1B — 29.27 (2024-03-07)
codegen-6B-multi — 28.71 (2024-03-07)
codegen-350M-multi — 22.94 (2024-03-07)
deepseek-coder-33b-base — 69.01 (2024-03-07)
2024-03-07 — deepseek-coder-33b-base: Average 69.01
Rank
Model
Average
Algorithmic
Control
API
Paper
Code
Year
1
deepseek-coder-33b-base
69.01
60.78
71.10
75.16
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
2
deepseek-coder-6.7b-base
63.40
54.74
65.79
69.68
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
3
starcoderbase
55.54
44.11
54.46
68.06
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
4
gpt-4-1106-preview
53.28
42.11
55.15
62.58
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
5
CodeLlama-13b-hf
52.78
41.41
57.25
59.68
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
6
deepseek-coder-1.3b-base
52.63
41.20
54.10
62.58
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
7
CodeLlama-34b-hf
49.66
38.55
53.98
56.45
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
8
CodeLlama-7b-hf
45.00
34.68
53.56
46.77
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
9
gpt-3.5-turbo-0301
40.86
31.24
37.48
53.87
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
10
incoder-6B
33.79
25.16
28.16
48.06
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
11
codegen-16B-multi
30.99
25.94
35.74
31.29
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
12
codegen-2B-multi
29.55
23.49
32.89
32.26
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
13
incoder-1B
29.27
21.06
22.89
43.87
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
14
codegen-6B-multi
28.71
23.60
34.80
27.74
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
15
codegen-350M-multi
22.94
16.30
26.06
26.45
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
gonglinyuan/safim
2024
1–15 / 15
페이지당
10
20
50
100