Benchmark Almanac

DeepSeek Coder 1.3B

DeepSeek Coder 1.3B.

DeepSeek Released November 2nd, 2023
4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
DeepSeek Nov 2023

DeepSeek Coder 1.3B

Open weights

No Epoch Capabilities Index score yet

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
MMLU 25.8% #83 of 85 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
ARC-Challenge 25.4% #74 of 75 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
WinoGrande 53.3% #75 of 76 Claim in Qwen2.5-Coder Technical Report, via Epoch AI

Math and science

BenchmarkScoreRankSource
GSM8K 4.40% #70 of 70 Claim in Qwen2.5-Coder Technical Report, via Epoch AI