Model comparison

DeepSeek Coder 1.3B vs INTELLECT-1

Neither DeepSeek Coder 1.3B nor INTELLECT-1 has enough public benchmark results to be ranked yet; the rows below show what has been published.

Last verified . 5 shared benchmarks.

DeepSeek Coder 1.3B DeepSeek

35.0

Unranked Sparse

Summary

  • They share 5 benchmarks with published results for both.
  • DeepSeek Coder 1.3B has downloadable open weights; the other is API-only.

Side by side

DeepSeek Coder 1.3B and INTELLECT-1 specifications
DeepSeek Coder 1.3BINTELLECT-1
ProviderDeepSeekHugging Face
Noometry Index35.0—
Released2023-11-022024-11-29
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked97

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

DeepSeek Coder 1.3B: 31.2 (#287), INTELLECT-1: —

Coding benchmarks
BenchmarkDeepSeek Coder 1.3BINTELLECT-1
BigCodeBench Instruct22.8%—
BigCodeBench Complete29.6%—
HumanEval+60.4%—
MBPP+54.8%—

Reasoning Not comparable

DeepSeek Coder 1.3B: —, INTELLECT-1: —

Reasoning benchmarks
BenchmarkDeepSeek Coder 1.3BINTELLECT-1
Epoch Capabilities Index63.6100.86
WinoGrande53.3%65.8%
BIG-Bench Hard—34.9%
HellaSwag—71.4%

Math Not comparable

DeepSeek Coder 1.3B: —, INTELLECT-1: —

Math benchmarks
BenchmarkDeepSeek Coder 1.3BINTELLECT-1
GSM8K4.4%38.6%

Knowledge Not comparable

DeepSeek Coder 1.3B: —, INTELLECT-1: —

Knowledge benchmarks
BenchmarkDeepSeek Coder 1.3BINTELLECT-1
ARC (AI2) Challenge25.4%54.5%
MMLU25.8%49.9%

Frequently asked questions

Is DeepSeek Coder 1.3B better than INTELLECT-1?

Neither DeepSeek Coder 1.3B nor INTELLECT-1 has enough public benchmark results to be ranked yet; the rows below show what has been published.

How many benchmarks do DeepSeek Coder 1.3B and INTELLECT-1 share?

5 benchmarks have published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and INTELLECT-1 has 7.

Related comparisons

Go deeper