Noometry

Model comparison

DeepSeek LLM 67B vs GPT-4.5

GPT-4.5 is the stronger model overall, scoring 37.2 to 24.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and GPT-4.5 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.5 leads 32.5 to 7.0.
  • The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 78.6% for GPT-4.5.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGPT-4.5
ProviderDeepSeekOpenAI
Noometry Index24.937.2
Released2023-11-292025-02-27
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1542

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

Category by category

Coding GPT-4.5 leads

DeepSeek LLM 67B: 31.9 (#278), GPT-4.5: 42.2 (#109)

BenchmarkDeepSeek LLM 67BGPT-4.5
LMArena Coding10961396
Aider Polyglot—44.9%
WeirdML—39.4%
LiveBench Coding—75.2%

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, GPT-4.5: 27.9 (#97)

BenchmarkDeepSeek LLM 67BGPT-4.5
Cybench—17.5%

Reasoning DeepSeek LLM 67B leads

DeepSeek LLM 67B: 16.5 (#304), GPT-4.5: 13.9 (#330)

BenchmarkDeepSeek LLM 67BGPT-4.5
LMArena Hard Prompts10701403
Epoch Capabilities Index110.5136.74
ARC-AGI-2—0.8%
SimpleBench—34.5%
ARC-AGI-1—10.3%
Chess Puzzles0%—
EnigmaEval—3.2%
LiveBench Reasoning—71.1%
LiveBench Data Analysis—64.3%
ForecastBench—61.7
LiveBench—69%

Math GPT-4.5 leads

DeepSeek LLM 67B: 8.7 (#324), GPT-4.5: 32.6 (#211)

BenchmarkDeepSeek LLM 67BGPT-4.5
OTIS Mock AIME 2024-20250.8%37.8%
LMArena Math11081412
MATH Level 56.4%78.6%
LiveBench Math—69.3%

Knowledge GPT-4.5 leads

DeepSeek LLM 67B: 7.0 (#313), GPT-4.5: 32.5 (#211)

BenchmarkDeepSeek LLM 67BGPT-4.5
GPQA Diamond24.6%68.7%
Humanity's Last Exam—5.4%
Confabulations—13.6%
LMArena Expert—1394

Multimodal Not comparable

DeepSeek LLM 67B: —, GPT-4.5: 37.6 (#71)

BenchmarkDeepSeek LLM 67BGPT-4.5
LMArena Vision—1195
VPCT—45%

Multilingual GPT-4.5 leads

DeepSeek LLM 67B: 29.4 (#267), GPT-4.5: 52.5 (#83)

BenchmarkDeepSeek LLM 67BGPT-4.5
LMArena Non-English10731413
LMArena Chinese11321421
LMArena French—1418
LMArena German—1457
LMArena Japanese—1416
LMArena Korean—1392
LMArena Russian—1419

Instruction Following GPT-4.5 leads

DeepSeek LLM 67B: 55.4 (#277), GPT-4.5: 72.6 (#134)

BenchmarkDeepSeek LLM 67BGPT-4.5
LMArena Instruction Following10791404
LiveBench Instruction Following—72.3%

Long Context GPT-4.5 leads

DeepSeek LLM 67B: 33.1 (#265), GPT-4.5: 40.4 (#155)

BenchmarkDeepSeek LLM 67BGPT-4.5
LMArena Longer Query10921406
Fiction.LiveBench—63.9%

Writing & Preference GPT-4.5 leads

DeepSeek LLM 67B: 31.6 (#282), GPT-4.5: 56.9 (#134)

BenchmarkDeepSeek LLM 67BGPT-4.5
LMArena Text11051417
LMArena Creative Writing10671394
LMArena Multi-Turn10821444
Short-Story Creative Writing—75.6%
EQ-Bench Creative Writing—1258
LiveBench Language—61.5%

Frequently asked questions

Is DeepSeek LLM 67B better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 37.2 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and GPT-4.5 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper