Noometry

Model comparison

DeepSeek LLM 67B vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 61.8 to 24.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 13 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GPT-6 Sol in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Sol leads 87.2 to 8.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 100% for GPT-6 Sol.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGPT-6 Sol
ProviderDeepSeekOpenAI
Noometry Index24.961.8
Released2023-11-292026-09-22
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked1545

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

Category by category

Coding GPT-6 Sol leads

DeepSeek LLM 67B: 31.9 (#278), GPT-6 Sol: 60.1 (#11)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
LMArena Coding10961447
DeepSWE—68.8%
FrontierCode—49.3%
LMArena WebDev—1688
SciCode—57.6%
ALE-Bench—2,462

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, GPT-6 Sol: 37.2 (#36)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
APEX-Agents—54.3%
GDP.pdf—26.4%
Vending-Bench 2—14,428

Reasoning GPT-6 Sol leads

DeepSeek LLM 67B: 16.5 (#304), GPT-6 Sol: 74.0 (#9)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
LMArena Hard Prompts10701418
Epoch Capabilities Index110.5162.72
ARC-AGI-2—89.6%
NYT Connections (extended)—90.1%
ARC-AGI-1—95.5%
CritPt—30.9%
Chess Puzzles0%—
EBR-Bench—53.3%
Mystery Game Puzzles—56%
DTBench—97.3%
LMCA—59.1%

Math GPT-6 Sol leads

DeepSeek LLM 67B: 8.7 (#324), GPT-6 Sol: 87.2 (#7)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
OTIS Mock AIME 2024-20250.8%100%
LMArena Math11081402
FrontierMath (Tiers 1-3)—89.8%
FrontierMath Tier 4—90%
ProofBench—83%
MATH Level 56.4%—

Knowledge GPT-6 Sol leads

DeepSeek LLM 67B: 7.0 (#313), GPT-6 Sol: 64.8 (#15)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
GPQA Diamond24.6%94.3%
SimpleQA Verified—60.7%
Vectara Hallucination Rate—6.5%
LMArena Expert—1439

Multimodal Not comparable

DeepSeek LLM 67B: —, GPT-6 Sol: 47.6 (#10)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
LMArena Vision—1245
Blueprint-Bench 2—36.9%
Furniture Assembly—58.3%

Multilingual GPT-6 Sol leads

DeepSeek LLM 67B: 29.4 (#267), GPT-6 Sol: 50.5 (#118)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
LMArena Non-English10731385
LMArena Chinese11321405
LMArena French—1410
LMArena German—1390
LMArena Japanese—1385
LMArena Korean—1341
LMArena Russian—1401
LMArena Spanish—1384

Instruction Following GPT-6 Sol leads

DeepSeek LLM 67B: 55.4 (#277), GPT-6 Sol: 74.5 (#94)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
LMArena Instruction Following10791412

Long Context GPT-6 Sol leads

DeepSeek LLM 67B: 33.1 (#265), GPT-6 Sol: 43.1 (#108)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
LMArena Longer Query10921411

Writing & Preference GPT-6 Sol leads

DeepSeek LLM 67B: 31.6 (#282), GPT-6 Sol: 71.9 (#18)

BenchmarkDeepSeek LLM 67BGPT-6 Sol
LMArena Text11051395
LMArena Creative Writing10671378
LMArena Multi-Turn10821412
EQ-Bench Creative Writing—2125

Frequently asked questions

Is DeepSeek LLM 67B better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and GPT-6 Sol share?

13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper