DeepSeek-Coder-V2-Lite-Base: benchmark scores, price and ranking
DeepSeek-Coder-V2-Lite-Base from deepseek-ai ranks #608 of 743 LLMs on the LLMs Tiger aggregate benchmark score (45.0), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- deepseek-ai
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2024-06-13 (source: epoch)
- Aggregate rank
- #608 of 743 (score 45.0)
Across the 2 benchmarks where at least ten models are scored, DeepSeek-Coder-V2-Lite-Base is in the top 10% on 0 and in the top half on 0.
DeepSeek-Coder-V2-Lite-Base benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 109 | #160 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| MMLU-Pro | 34.4% | #112 of 136 | HuggingFace MMLU-Pro leaderboard | 2026-10-13 |
About DeepSeek-Coder-V2-Lite-Base
DeepSeek-Coder-V2-Lite-Base is an open-weight model that can run on your own hardware from deepseek-ai. It was released on 2024-06-13, according to Epoch AI. No API price is listed for it yet. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where DeepSeek-Coder-V2-Lite-Base stands
On our aggregate score, DeepSeek-Coder-V2-Lite-Base is #608 of 743 ranked models, in the lower half. Its score is 45.0; the scale is centred on 50, so it sits 5.0 points below the typical model. That beats 18% of the ranked field. Among the 7 ranked deepseek-ai models it is #7. The next one up is deepseek-math-7b-instruct at 45.2.
DeepSeek-Coder-V2-Lite-Base, benchmark by benchmark
DeepSeek-Coder-V2-Lite-Base lands below the middle on Epoch ECI: 109, #160 of 204, with 78% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is Mistral 7B v0.3 at 109. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so DeepSeek-Coder-V2-Lite-Base is 18 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
MMLU-Pro is a weak spot. DeepSeek-Coder-V2-Lite-Base scores 34.4%, #112 of 136, behind 82% of the models measured. The leader, Darwin-180B-RSI, reaches 88.1%. It covers 57-subject knowledge + reasoning. The board median is 55.3%, so DeepSeek-Coder-V2-Lite-Base is 20.9 points below it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.
Strengths and weaknesses
DeepSeek-Coder-V2-Lite-Base has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.
Release history
The deepseek-ai model released before it was DeepSeek-V2-Chat on 2024-05-06, which scores 47.8. The next one was DeepSeek-V2.5 on 2024-09-05, at 50.9.
Reading these numbers
The 2 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (1), HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #605 ollama/hermes3:8b-llama3.1-fp16 (45.1)
- #606 ollama/wojtek/opencodeinterpreter:6.7b (45.1)
- #607 DeepSeek-V3 (45.1)
- #609 mistral-small-3-2501 (45.0)
- #610 GLM-4.6 (45.0)
- #611 qwen2.5-32b-instruct (45.0)
More from deepseek-ai
- DeepSeek R1 (0528) (#33, 53.6)
- DeepSeek-V2.5 (#162, 50.9)
- DeepSeek-V2-Chat (#404, 47.8)
- DeepSeek-V2 (#505, 46.6)
- DeepSeek-Coder-V2-Lite-Instruct (#546, 46.0)
- deepseek-math-7b-instruct (#604, 45.2)
Compare it on the live leaderboard → · How the aggregate score works