Noometry

Model comparison

DeepSeek LLM 67B vs Grok Build 0.1

Grok Build 0.1 is the stronger model overall, scoring 35.8 to 24.8 on the Noometry Index.

Last verified . 0 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.8

Rank #341 Confirmed

Grok Build 0.1 xAI

35.8

Rank #214 Reported

Summary

  • The widest gap is in reasoning, where Grok Build 0.1 leads 31.3 to 15.9.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGrok Build 0.1
ProviderDeepSeekxAI
Noometry Index24.835.8
Released2023-11-292026-04-16
WeightsOpenProprietary
Context window—256K
Max output—256K
Input $ / M tokens—$1
Output $ / M tokens—$2
Results tracked153

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

Category by category

Coding Grok Build 0.1 leads

DeepSeek LLM 67B: 31.3 (#273), Grok Build 0.1: 42.5 (#90)

BenchmarkDeepSeek LLM 67BGrok Build 0.1
SciCode—50.2%
LMArena Coding1096—

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Grok Build 0.1: 22.5 (#122)

BenchmarkDeepSeek LLM 67BGrok Build 0.1
GBAEval—2.4%

Reasoning Grok Build 0.1 leads

DeepSeek LLM 67B: 15.9 (#300), Grok Build 0.1: 31.3 (#73)

BenchmarkDeepSeek LLM 67BGrok Build 0.1
CritPt—9.1%
Chess Puzzles0%—
LMArena Hard Prompts1070—
Epoch Capabilities Index110.54—

Math Not comparable

DeepSeek LLM 67B: 8.1 (#318), Grok Build 0.1: —

BenchmarkDeepSeek LLM 67BGrok Build 0.1
OTIS Mock AIME 2024-20250.8%—
LMArena Math1108—
MATH Level 56.4%—

Knowledge Not comparable

DeepSeek LLM 67B: 7.1 (#308), Grok Build 0.1: —

BenchmarkDeepSeek LLM 67BGrok Build 0.1
GPQA Diamond24.6%—

Multilingual Not comparable

DeepSeek LLM 67B: 29.5 (#262), Grok Build 0.1: —

BenchmarkDeepSeek LLM 67BGrok Build 0.1
LMArena Non-English1073—
LMArena Chinese1132—

Instruction Following Not comparable

DeepSeek LLM 67B: 55.7 (#272), Grok Build 0.1: —

BenchmarkDeepSeek LLM 67BGrok Build 0.1
LMArena Instruction Following1079—

Long Context Not comparable

DeepSeek LLM 67B: 33.1 (#260), Grok Build 0.1: —

BenchmarkDeepSeek LLM 67BGrok Build 0.1
LMArena Longer Query1092—

Writing & Preference Not comparable

DeepSeek LLM 67B: 31.8 (#277), Grok Build 0.1: —

BenchmarkDeepSeek LLM 67BGrok Build 0.1
LMArena Text1105—
LMArena Creative Writing1067—
LMArena Multi-Turn1082—

Frequently asked questions

Is DeepSeek LLM 67B better than Grok Build 0.1?

Grok Build 0.1 is the stronger model overall, scoring 35.8 to 24.8 on the Noometry Index.

Is DeepSeek LLM 67B or Grok Build 0.1 better for coding?

Grok Build 0.1 scores higher on coding benchmarks: 42.5 versus 31.3 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Grok Build 0.1 share?

0 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Grok Build 0.1 has 3.

Related comparisons

Go deeper