ModelTape
All modelsNew releasesRankingsRuns on my GPUOpen the app →
ModelTape / Models / DeepSeek-Coder-V2-Lite-Base
— · closed

DeepSeek-Coder-V2-Lite-Base

DeepSeek-Coder-V2-Lite-Base is a closed language model from —, released June 13, 2024. On the Epoch Capabilities Index it scores 99.7, rank 215 of 256 rated models.

Check it against your own PC →

Lab
—
Released
June 13, 2024
Weights
closed
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
99.7 #215

Benchmark results

Benchmark (Epoch AI)Score
MMLU47.3%

Links

Epoch AI benchmarks

Models with a similar score

Gemma 7B · Mistral 7B v0.1 · Yi-9B · Qwen-14B · LLaMA-65B · Falcon 2 11B · Nemotron-4 15B · internlm-20b

More from —

Qwen2.5-Coder-14B · Qwen2.5-Coder-3B · Qwen2.5-Coder-0.5B · CodeQwen1.5-7B · Yi-9B · Qwen-1_8B · internlm-20b · internlm-7b

Data updated Thu, 12 Nov 2026 09:42 UTC. Benchmarks, Capabilities Index and model announcements: Epoch AI, “Capabilities & benchmarking” and “Data on AI models” (CC BY 4.0); category scores are ModelTape's own fit on Epoch's results. Releases and prices: models.dev (MIT). Sizes and quantizations: Hugging Face. “Runs on” figures are estimates from model size, quantization and memory bandwidth (±30–50%).
Live app · All models · New releases · Rankings · 6 GB · 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · Legal notice (Impressum) · Privacy