Noometry

Model comparison

DeepSeek LLM 67B vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.9 to 24.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.6 leads 67.0 to 8.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 99.2% for Grok 4.6.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGrok 4.6
ProviderDeepSeekxAI
Noometry Index24.956.9
Released2023-11-292026-08-12
WeightsOpenProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked1549

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

Category by category

Coding Grok 4.6 leads

DeepSeek LLM 67B: 31.9 (#278), Grok 4.6: 58.5 (#16)

BenchmarkDeepSeek LLM 67BGrok 4.6
LMArena Coding10961465
DeepSWE—67.5%
FrontierCode—48%
CursorBench—41.4%
LMArena WebDev—1617
FrontierSWE—25.3%
SciCode—56.5%
WeirdML—67.3%
ALE-Bench—1,508

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Grok 4.6: 39.4 (#27)

BenchmarkDeepSeek LLM 67BGrok 4.6
APEX-Agents—65.3%
GDP.pdf—17.2%
Vending-Bench 2—9,047

Reasoning Grok 4.6 leads

DeepSeek LLM 67B: 16.5 (#304), Grok 4.6: 61.4 (#20)

BenchmarkDeepSeek LLM 67BGrok 4.6
Chess Puzzles0%40%
LMArena Hard Prompts10701447
Epoch Capabilities Index110.5156.44
ARC-AGI-2—67.1%
SimpleBench—75.9%
NYT Connections (extended)—80%
ARC-AGI-1—87.5%
CritPt—19.7%
EBR-Bench—30.5%
Mystery Game Puzzles—34%
DTBench—97.3%
LMCA—48.5%

Math Grok 4.6 leads

DeepSeek LLM 67B: 8.7 (#324), Grok 4.6: 67.0 (#24)

BenchmarkDeepSeek LLM 67BGrok 4.6
OTIS Mock AIME 2024-20250.8%99.2%
LMArena Math11081423
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
ProofBench—51%
MATH Level 56.4%—

Knowledge Grok 4.6 leads

DeepSeek LLM 67B: 7.0 (#313), Grok 4.6: 63.3 (#20)

BenchmarkDeepSeek LLM 67BGrok 4.6
GPQA Diamond24.6%94%
SimpleQA Verified—49.3%
LMArena Expert—1467

Multimodal Not comparable

DeepSeek LLM 67B: —, Grok 4.6: 43.6 (#23)

BenchmarkDeepSeek LLM 67BGrok 4.6
LMArena Vision—1263
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual Grok 4.6 leads

DeepSeek LLM 67B: 29.4 (#267), Grok 4.6: 53.0 (#74)

BenchmarkDeepSeek LLM 67BGrok 4.6
LMArena Non-English10731420
LMArena Chinese11321480
LMArena French—1461
LMArena German—1431
LMArena Japanese—1376
LMArena Korean—1397
LMArena Russian—1422
LMArena Spanish—1404

Instruction Following Grok 4.6 leads

DeepSeek LLM 67B: 55.4 (#277), Grok 4.6: 75.4 (#63)

BenchmarkDeepSeek LLM 67BGrok 4.6
LMArena Instruction Following10791431

Long Context Grok 4.6 leads

DeepSeek LLM 67B: 33.1 (#265), Grok 4.6: 44.5 (#66)

BenchmarkDeepSeek LLM 67BGrok 4.6
LMArena Longer Query10921454

Writing & Preference Grok 4.6 leads

DeepSeek LLM 67B: 31.6 (#282), Grok 4.6: 62.3 (#80)

BenchmarkDeepSeek LLM 67BGrok 4.6
LMArena Text11051428
LMArena Creative Writing10671428
LMArena Multi-Turn10821425

Frequently asked questions

Is DeepSeek LLM 67B better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Grok 4.6 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper