Noometry

Model comparison

DeepSeek LLM 67B vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.8 to 24.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Grok 4.3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 7.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 93.3% for Grok 4.3.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGrok 4.3
ProviderDeepSeekxAI
Noometry Index24.943.8
Released2023-11-292026-04-17
WeightsOpenProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked1540

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

Category by category

Coding Grok 4.3 leads

DeepSeek LLM 67B: 31.9 (#278), Grok 4.3: 41.6 (#121)

BenchmarkDeepSeek LLM 67BGrok 4.3
LMArena Coding10961415
LMArena WebDev—1357
SciCode—47.3%
WeirdML—49.9%
ALE-Bench—944.17

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Grok 4.3: 27.7 (#99)

BenchmarkDeepSeek LLM 67BGrok 4.3
GDP.pdf—8%
LMArena Search—1165
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

DeepSeek LLM 67B: 16.5 (#304), Grok 4.3: 35.9 (#68)

BenchmarkDeepSeek LLM 67BGrok 4.3
Chess Puzzles0%25%
LMArena Hard Prompts10701396
Epoch Capabilities Index110.5149.16
NYT Connections (extended)—55.2%
CritPt—8%
DTBench—90.7%
LMCA—38.3%
ForecastBench—60.3

Math Grok 4.3 leads

DeepSeek LLM 67B: 8.7 (#324), Grok 4.3: 46.0 (#74)

BenchmarkDeepSeek LLM 67BGrok 4.3
OTIS Mock AIME 2024-20250.8%93.3%
LMArena Math11081388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
ProofBench—11%
MATH Level 56.4%—

Knowledge Grok 4.3 leads

DeepSeek LLM 67B: 7.0 (#313), Grok 4.3: 52.5 (#62)

BenchmarkDeepSeek LLM 67BGrok 4.3
GPQA Diamond24.6%88.8%
SimpleQA Verified—33.2%
LMArena Expert—1385

Multimodal Not comparable

DeepSeek LLM 67B: —, Grok 4.3: 31.6 (#104)

BenchmarkDeepSeek LLM 67BGrok 4.3
LMArena Vision—1229
Blueprint-Bench 2—0%

Multilingual Grok 4.3 leads

DeepSeek LLM 67B: 29.4 (#267), Grok 4.3: 50.5 (#120)

BenchmarkDeepSeek LLM 67BGrok 4.3
LMArena Non-English10731385
LMArena Chinese11321422
LMArena French—1412
LMArena German—1395
LMArena Japanese—1379
LMArena Korean—1356
LMArena Russian—1399
LMArena Spanish—1398

Instruction Following Grok 4.3 leads

DeepSeek LLM 67B: 55.4 (#277), Grok 4.3: 72.1 (#140)

BenchmarkDeepSeek LLM 67BGrok 4.3
LMArena Instruction Following10791366

Long Context Grok 4.3 leads

DeepSeek LLM 67B: 33.1 (#265), Grok 4.3: 42.5 (#123)

BenchmarkDeepSeek LLM 67BGrok 4.3
LMArena Longer Query10921393

Writing & Preference Grok 4.3 leads

DeepSeek LLM 67B: 31.6 (#282), Grok 4.3: 58.5 (#118)

BenchmarkDeepSeek LLM 67BGrok 4.3
LMArena Text11051397
LMArena Creative Writing10671380
LMArena Multi-Turn10821406
EQ-Bench 4—1075

Frequently asked questions

Is DeepSeek LLM 67B better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Grok 4.3 better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Grok 4.3 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper