Noometry

Model comparison

DeepSeek Coder 1.3B vs GPT-3.5-turbo

GPT-3.5-turbo has enough public results to be ranked (#345); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

Last verified . 9 shared benchmarks.

DeepSeek Coder 1.3B DeepSeek

34.5

Unranked Sparse

GPT-3.5-turbo OpenAI

23.1

Rank #345 Confirmed

Summary

  • They share 9 benchmarks with published results for both. DeepSeek Coder 1.3B scores higher in 1 category and GPT-3.5-turbo in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in coding, where DeepSeek Coder 1.3B leads 30.7 to 23.5.
  • The biggest single-benchmark swing is BigCodeBench Complete: 29.6% for DeepSeek Coder 1.3B and 50.6% for GPT-3.5-turbo.
  • DeepSeek Coder 1.3B has downloadable open weights; the other is API-only.

Side by side

DeepSeek Coder 1.3BGPT-3.5-turbo
ProviderDeepSeekOpenAI
Noometry Index34.523.1
Released2023-11-022023-03-01
WeightsOpenProprietary
Context window—16K
Max output—4K
Input $ / M tokens—$0.50
Output $ / M tokens—$1.50
Results tracked944

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

Category by category

Coding DeepSeek Coder 1.3B leads

DeepSeek Coder 1.3B: 30.7 (#282), GPT-3.5-turbo: 23.5 (#326)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
BigCodeBench Instruct22.8%39.1%
BigCodeBench Complete29.6%50.6%
HumanEval+60.4%70.7%
MBPP+54.8%69.7%
WeirdML—3.5%
LMArena Coding—1137

Agentic & Tool Use Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: —

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
METR Time Horizons—21.5%

Reasoning Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: 13.3 (#328)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
Epoch Capabilities Index62.18118.48
WinoGrande53.3%81.6%
Chess Puzzles—0%
LMArena Hard Prompts—1108
Mystery Game Puzzles—3%
DTBench—48.5%
LMCA—9.7%
Adversarial NLI—58.1%
BIG-Bench Hard—61.6%
CommonsenseQA 2.0—57%
ForecastBench—50.4

Math Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: 6.0 (#321)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
GSM8K4.4%57.8%
FrontierMath (Tiers 1-3)—0%
OTIS Mock AIME 2024-2025—2.2%
LMArena Math—1142
MATH Level 5—15.9%

Knowledge Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: 10.0 (#298)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
ARC (AI2) Challenge25.4%87.4%
MMLU25.8%71.4%
GPQA Diamond—28%
LMArena Expert—1070
BoolQ—87%
OpenBookQA—86%
TriviaQA—85.8%

Multilingual Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: 31.6 (#253)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
LMArena Non-English—1108
LMArena Chinese—1075
LMArena French—1117
LMArena German—1090
LMArena Japanese—1043
LMArena Korean—1019
LMArena Russian—1123
LMArena Spanish—1120

Instruction Following Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: 58.1 (#257)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
LMArena Instruction Following—1119

Long Context Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: 34.0 (#249)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
LMArena Longer Query—1121

Writing & Preference Not comparable

DeepSeek Coder 1.3B: —, GPT-3.5-turbo: 25.4 (#300)

BenchmarkDeepSeek Coder 1.3BGPT-3.5-turbo
LMArena Text—1125
LMArena Creative Writing—1092
EQ-Bench Creative Writing—451
LMArena Multi-Turn—1117

Frequently asked questions

Is DeepSeek Coder 1.3B better than GPT-3.5-turbo?

GPT-3.5-turbo has enough public results to be ranked (#345); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 1.3B or GPT-3.5-turbo better for coding?

DeepSeek Coder 1.3B scores higher on coding benchmarks: 30.7 versus 23.5 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 1.3B and GPT-3.5-turbo share?

9 benchmarks have published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and GPT-3.5-turbo has 44.

Related comparisons

Go deeper