Noometry

Model comparison

Codellama 34b Instruct vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.8 to 30.8 on the Noometry Index.

Last verified . 10 shared benchmarks.

Codellama 34b Instruct Meta

30.8

Rank #287 Confirmed

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and Grok 4.3 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4.3 leads 58.5 to 28.2.
  • Codellama 34b Instruct has downloadable open weights; the other is API-only.

Side by side

Codellama 34b InstructGrok 4.3
ProviderMetaxAI
Noometry Index30.843.8
Released—2026-04-17
WeightsOpenProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked1440

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

Category by category

Coding Grok 4.3 leads

Codellama 34b Instruct: 28.5 (#314), Grok 4.3: 41.6 (#121)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Coding10461415
LMArena WebDev—1357
SciCode—47.3%
WeirdML—49.9%
BigCodeBench Instruct29%—
BigCodeBench Complete37.1%—
ALE-Bench—944.17
HumanEval+43.9%—
MBPP+56.3%—

Agentic & Tool Use Not comparable

Codellama 34b Instruct: —, Grok 4.3: 27.7 (#99)

BenchmarkCodellama 34b InstructGrok 4.3
GDP.pdf—8%
LMArena Search—1165
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

Codellama 34b Instruct: 19.6 (#255), Grok 4.3: 35.9 (#68)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Hard Prompts10321396
NYT Connections (extended)—55.2%
CritPt—8%
Chess Puzzles—25%
DTBench—90.7%
LMCA—38.3%
Epoch Capabilities Index—149.16
ForecastBench—60.3

Math Grok 4.3 leads

Codellama 34b Instruct: 31.0 (#230), Grok 4.3: 46.0 (#74)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Math10561388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
OTIS Mock AIME 2024-2025—93.3%
ProofBench—11%

Knowledge Not comparable

Codellama 34b Instruct: —, Grok 4.3: 52.5 (#62)

BenchmarkCodellama 34b InstructGrok 4.3
GPQA Diamond—88.8%
SimpleQA Verified—33.2%
LMArena Expert—1385

Multimodal Not comparable

Codellama 34b Instruct: —, Grok 4.3: 31.6 (#104)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Vision—1229
Blueprint-Bench 2—0%

Multilingual Grok 4.3 leads

Codellama 34b Instruct: 25.8 (#284), Grok 4.3: 50.5 (#120)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Non-English10111385
LMArena Chinese9761422
LMArena French—1412
LMArena German—1395
LMArena Japanese—1379
LMArena Korean—1356
LMArena Russian—1399
LMArena Spanish—1398

Instruction Following Grok 4.3 leads

Codellama 34b Instruct: 52.2 (#291), Grok 4.3: 72.1 (#140)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Instruction Following10281366

Long Context Grok 4.3 leads

Codellama 34b Instruct: 30.9 (#284), Grok 4.3: 42.5 (#123)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Longer Query10131393

Writing & Preference Grok 4.3 leads

Codellama 34b Instruct: 28.2 (#297), Grok 4.3: 58.5 (#118)

BenchmarkCodellama 34b InstructGrok 4.3
LMArena Text10661397
LMArena Creative Writing10321380
LMArena Multi-Turn10151406
EQ-Bench 4—1075

Frequently asked questions

Is Codellama 34b Instruct better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 30.8 on the Noometry Index.

Is Codellama 34b Instruct or Grok 4.3 better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 28.5 in the Noometry coding category.

How many benchmarks do Codellama 34b Instruct and Grok 4.3 share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper