DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
1.5b
14b
36.3K Pulls Updated 10 days ago
Updated 10 days ago
10 days ago
12bdda054d23 · 9.0GB
model
archqwen2
·
parameters14.8B
·
quantizationQ4_K_M
9.0GB
params
{
"temperature": 0.6,
"top_p": 0.95
}
33B
template
{{- if .System }}{{ .System }}{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice
387B
license
MIT License
Copyright (c) 2025 Agentica
Permission is hereby granted, free of charge, to any perso
1.1kB
Readme
Through a joint collaboration between the Agentica team and Together AI, DeepCoder-14B-Preview is a code reasoning model finetuned from Deepseek-R1-Distilled-Qwen-14B via distributed RL. It achieves an impressive 60.6% Pass@1 accuracy on LiveCodeBench (+8% improvement), matching the performance of o3-mini-2025-01-031 (Low) and o1-2024-12-17 with just 14B parameters
Evaluation
| Model | LCB (v5)(8/1/24-2/1/25) | Codeforces Rating | Codeforces Percentile | HumanEval+ |
|---|---|---|---|---|
| DeepCoder-14B-Preview | 60.6 | 1936 | 95.3 | 92.6 |
| DeepSeek-R1-Distill-Qwen-14B | 53.0 | 1791 | 92.7 | 92.0 |
| O1-2024-12-17 (Low) | 59.5 | 1991 | 96.1 | 90.8 |
| O3-Mini-2025-1-31 (Low) | 60.9 | 1918 | 94.9 | 92.6 |
| O1-Preview | 42.7 | 1658 | 88.5 | 89 |
| Deepseek-R1 | 62.8 | 1948 | 95.4 | 92.6 |
| Llama-4-Behemoth | 49.4 | - | - | - |