Noometry

Model comparison

DeepSeek LLM 67B vs GPT-5 Nano

GPT-5 Nano is the stronger model overall, scoring 33.5 to 24.9 on the Noometry Index.

Last verified . 15 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

GPT-5 Nano OpenAI

33.5

Rank #241 Confirmed

Summary

  • They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 2 categories and GPT-5 Nano in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5 Nano leads 35.9 to 7.0.
  • The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 95.2% for GPT-5 Nano.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGPT-5 Nano
ProviderDeepSeekOpenAI
Noometry Index24.933.5
Released2023-11-292025-08-07
WeightsOpenProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.40
Results tracked1549

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

Category by category

Coding GPT-5 Nano leads

DeepSeek LLM 67B: 31.9 (#278), GPT-5 Nano: 33.6 (#254)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
LMArena Coding10961351
SWE-bench Verified (bash only)—34.8%
WeirdML—38.1%
ALE-Bench—718.67

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, GPT-5 Nano: 25.8 (#106)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
Terminal-Bench—21.8%
Berkeley Function Calling Leaderboard—51.5%

Reasoning Too close to call

DeepSeek LLM 67B: 16.5 (#304), GPT-5 Nano: 16.3 (#306)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
Chess Puzzles0%27%
LMArena Hard Prompts10701328
Epoch Capabilities Index110.5139.38
ARC-AGI-2—2.6%
Kagi LLM Benchmark—62.2%
ARC-AGI-1—20.7%
Mystery Game Puzzles—9%
DTBench—62.7%
LMCA—7.9%
ForecastBench—59.1

Math GPT-5 Nano leads

DeepSeek LLM 67B: 8.7 (#324), GPT-5 Nano: 29.4 (#241)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
OTIS Mock AIME 2024-20250.8%81.1%
LMArena Math11081317
MATH Level 56.4%95.2%
FrontierMath (Tiers 1-3)—20%
FrontierMath Tier 4—2.4%
ProofBench—12%
Omni-MATH—54.6%
FrontierMath (Feb 2025 set)—8.3%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GPT-5 Nano leads

DeepSeek LLM 67B: 7.0 (#313), GPT-5 Nano: 35.9 (#178)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
GPQA Diamond24.6%69.4%
SimpleQA Verified—11.7%
MMLU-Pro—77.8%
Vectara Hallucination Rate—10.5%
GPQA (HELM)—67.9%
LMArena Expert—1321

Multimodal Not comparable

DeepSeek LLM 67B: —, GPT-5 Nano: 31.3 (#108)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
LMArena Vision—1159
VPCT—37.2%

Multilingual GPT-5 Nano leads

DeepSeek LLM 67B: 29.4 (#267), GPT-5 Nano: 45.3 (#172)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
LMArena Non-English10731313
LMArena Chinese11321356
LMArena German—1327
LMArena Japanese—1226
LMArena Korean—1269
LMArena Russian—1296
LMArena Spanish—1360

Instruction Following GPT-5 Nano leads

DeepSeek LLM 67B: 55.4 (#277), GPT-5 Nano: 75.0 (#79)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
LMArena Instruction Following10791306
IFEval—93.2%

Long Context DeepSeek LLM 67B leads

DeepSeek LLM 67B: 33.1 (#265), GPT-5 Nano: 31.3 (#281)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
LMArena Longer Query10921312
Fiction.LiveBench—44.4%

Writing & Preference GPT-5 Nano leads

DeepSeek LLM 67B: 31.6 (#282), GPT-5 Nano: 39.1 (#249)

BenchmarkDeepSeek LLM 67BGPT-5 Nano
LMArena Text11051320
LMArena Creative Writing10671249
LMArena Multi-Turn10821311
EQ-Bench Creative Writing—705
WildBench—80.6%

Frequently asked questions

Is DeepSeek LLM 67B better than GPT-5 Nano?

GPT-5 Nano is the stronger model overall, scoring 33.5 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or GPT-5 Nano better for coding?

GPT-5 Nano scores higher on coding benchmarks: 33.6 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and GPT-5 Nano share?

15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-5 Nano has 49.

Related comparisons

Go deeper