Noometry

Model comparison

DeepSeek LLM 67B vs Grok 4.20 Multi-Agent

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 24.8 on the Noometry Index.

Last verified . 10 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.8

Rank #341 Confirmed

Grok 4.20 Multi-Agent xAI

45.5

Rank #62 Confirmed

Summary

  • They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Grok 4.20 Multi-Agent in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.20 Multi-Agent leads 39.7 to 7.1.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGrok 4.20 Multi-Agent
ProviderDeepSeekxAI
Noometry Index24.845.5
Released2023-11-292026-03-09
WeightsOpenProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked1520

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

Category by category

Coding Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 31.3 (#273), Grok 4.20 Multi-Agent: 42.4 (#91)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Coding10961458

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Grok 4.20 Multi-Agent: —

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Search—1204

Reasoning Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 15.9 (#300), Grok 4.20 Multi-Agent: 42.4 (#44)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Hard Prompts10701448
NYT Connections (extended)—89.6%
Chess Puzzles0%—
Epoch Capabilities Index110.54—

Math Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 8.1 (#318), Grok 4.20 Multi-Agent: 36.6 (#106)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Math11081441
OTIS Mock AIME 2024-20250.8%—
MATH Level 56.4%—

Knowledge Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 7.1 (#308), Grok 4.20 Multi-Agent: 39.7 (#116)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
GPQA Diamond24.6%—
LMArena Expert—1445

Multimodal Not comparable

DeepSeek LLM 67B: —, Grok 4.20 Multi-Agent: 39.8 (#44)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Vision—1259

Multilingual Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 29.5 (#262), Grok 4.20 Multi-Agent: 54.6 (#40)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Non-English10731440
LMArena Chinese11321475
LMArena French—1467
LMArena German—1456
LMArena Japanese—1405
LMArena Korean—1416
LMArena Russian—1457
LMArena Spanish—1447

Instruction Following Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 55.7 (#272), Grok 4.20 Multi-Agent: 75.0 (#80)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Instruction Following10791420

Long Context Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 33.1 (#260), Grok 4.20 Multi-Agent: 43.7 (#84)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Longer Query10921430

Writing & Preference Grok 4.20 Multi-Agent leads

DeepSeek LLM 67B: 31.8 (#277), Grok 4.20 Multi-Agent: 64.1 (#57)

BenchmarkDeepSeek LLM 67BGrok 4.20 Multi-Agent
LMArena Text11051450
LMArena Creative Writing10671435
LMArena Multi-Turn10821451

Frequently asked questions

Is DeepSeek LLM 67B better than Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 24.8 on the Noometry Index.

Is DeepSeek LLM 67B or Grok 4.20 Multi-Agent better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 31.3 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Grok 4.20 Multi-Agent share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Grok 4.20 Multi-Agent has 20.

Related comparisons

Go deeper