Benchmark Almanac

DeepSeek-Coder-V2-Lite-Base

DeepSeek-Coder-V2-Lite-Base.

Released 13 Jun 2024
5
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Jun 2024

DeepSeek-Coder-V2-Lite-Base

108.8 #228 of 271
Epoch Capabilities Index

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
ARC-Challenge 57.3% #36 of 75 Epoch AI
WinoGrande 72.9% #41 of 76 Epoch AI
MMLU 60.5% #81 of 127 Epoch AI
MMLU-Pro 34.4% #172 of 212 Official leaderboard

Math and science

BenchmarkScoreRankSource
GSM8K 67.1% #25 of 82 Epoch AI

The lab's models over time

's models in color, against every other model on the Epoch Capabilities Index, by release date.

50 75 100 125 150 175 2023 2024 2025 2026 2027 Qwen2.5-Coder-0.5B Qwen2.5-Coder-14B Qwen2.5-Coder-3B CodeQwen1.5-7B internlm-20b internlm-7b open_llama_7b 50 75 100 125 150 175 2023 2024 2025 2026 2027 Qwen2.5-Coder-0.5B Qwen2.5-Coder-14B