Noometry

Model comparison

DeepSeek LLM 67B vs GPT-4o

GPT-4o is the stronger model overall, scoring 28.6 to 24.9 on the Noometry Index.

Last verified . 15 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

GPT-4o OpenAI

28.6

Rank #324 Confirmed

Summary

  • They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 2 categories and GPT-4o in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4o leads 28.8 to 7.0.
  • The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 53.3% for GPT-4o.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGPT-4o
ProviderDeepSeekOpenAI
Noometry Index24.928.6
Released2023-11-292024-05-13
WeightsOpenProprietary
Context window—128K
Max output—16K
Input $ / M tokens—$2.50
Output $ / M tokens—$10
Results tracked1572

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

Category by category

Coding DeepSeek LLM 67B leads

DeepSeek LLM 67B: 31.9 (#278), GPT-4o: 24.8 (#328)

BenchmarkDeepSeek LLM 67BGPT-4o
LMArena Coding10961297
SWE-bench Verified—31%
SWE-bench Verified (bash only)—21.6%
Aider Polyglot—45.3%
GSO—0%
WeirdML—25.1%
BigCodeBench Instruct—51.1%
LiveBench Coding—51.4%
BigCodeBench Complete—61.1%
CadEval—26%
HumanEval+—87.2%
MBPP+—72.2%

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, GPT-4o: 21.0 (#141)

BenchmarkDeepSeek LLM 67BGPT-4o
GDPval—9.9%
TheAgentCompany—8.6%
Cybench—12.5%
BALROG—32.3%
LMArena Search—1006
METR Time Horizons—40.8%

Reasoning DeepSeek LLM 67B leads

DeepSeek LLM 67B: 16.5 (#304), GPT-4o: 9.4 (#343)

BenchmarkDeepSeek LLM 67BGPT-4o
Chess Puzzles0%13%
LMArena Hard Prompts10701281
Epoch Capabilities Index110.5128.97
ARC-AGI-2—0%
SimpleBench—17.8%
ARC-AGI-1—4.5%
CritPt—0%
EnigmaEval—0.8%
LiveBench Reasoning—55.8%
DTBench—64.5%
LiveBench Data Analysis—60.9%
LMCA—16.6%
ForecastBench—57.7
LiveBench—55.3%

Math GPT-4o leads

DeepSeek LLM 67B: 8.7 (#324), GPT-4o: 10.6 (#312)

BenchmarkDeepSeek LLM 67BGPT-4o
OTIS Mock AIME 2024-20250.8%6.4%
LMArena Math11081285
MATH Level 56.4%53.3%
FrontierMath (Tiers 1-3)—0.4%
Omni-MATH—29.3%
LiveBench Math—49.5%
FrontierMath (Feb 2025 set)—0.3%

Knowledge GPT-4o leads

DeepSeek LLM 67B: 7.0 (#313), GPT-4o: 28.8 (#242)

BenchmarkDeepSeek LLM 67BGPT-4o
GPQA Diamond24.6%49.2%
Humanity's Last Exam—2.7%
SimpleQA Verified—26%
MMLU-Pro—71.3%
Confabulations—15.3%
Vectara Hallucination Rate—9.6%
GPQA (HELM)—52%
LMArena Expert—1250
MMLU—88.1%

Multimodal Not comparable

DeepSeek LLM 67B: —, GPT-4o: 34.5 (#91)

BenchmarkDeepSeek LLM 67BGPT-4o
LMArena Vision—1137
Video-MME—71.9%
GeoBench—71%
VPCT—40%
ScienceQA—88.5%

Multilingual GPT-4o leads

DeepSeek LLM 67B: 29.4 (#267), GPT-4o: 43.2 (#186)

BenchmarkDeepSeek LLM 67BGPT-4o
LMArena Non-English10731283
LMArena Chinese11321277
LMArena French—1304
LMArena German—1282
LMArena Japanese—1257
LMArena Korean—1234
LMArena Russian—1286
LMArena Spanish—1292

Instruction Following GPT-4o leads

DeepSeek LLM 67B: 55.4 (#277), GPT-4o: 66.6 (#207)

BenchmarkDeepSeek LLM 67BGPT-4o
LMArena Instruction Following10791278
LiveBench Instruction Following—68.6%
IFEval—81.7%

Long Context GPT-4o leads

DeepSeek LLM 67B: 33.1 (#265), GPT-4o: 39.4 (#179)

BenchmarkDeepSeek LLM 67BGPT-4o
LMArena Longer Query10921289
Fiction.LiveBench—66.7%

Writing & Preference GPT-4o leads

DeepSeek LLM 67B: 31.6 (#282), GPT-4o: 52.6 (#166)

BenchmarkDeepSeek LLM 67BGPT-4o
LMArena Text11051300
LMArena Creative Writing10671292
LMArena Multi-Turn10821302
Short-Story Creative Writing—81.8%
WildBench—82.8%
LiveBench Language—47.6%

Frequently asked questions

Is DeepSeek LLM 67B better than GPT-4o?

GPT-4o is the stronger model overall, scoring 28.6 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or GPT-4o better for coding?

DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 24.8 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and GPT-4o share?

15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-4o has 72.

Related comparisons

Go deeper