Noometry

Model comparison

Codellama 34b Instruct vs Grok 4.5

Grok 4.5 is the stronger model overall, scoring 55.0 to 30.8 on the Noometry Index.

Last verified . 10 shared benchmarks.

Codellama 34b Instruct Meta

30.8

Rank #287 Confirmed

Grok 4.5 xAI

55.0

Rank #25 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and Grok 4.5 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4.5 leads 65.8 to 28.2.
  • Codellama 34b Instruct has downloadable open weights; the other is API-only.

Side by side

Codellama 34b InstructGrok 4.5
ProviderMetaxAI
Noometry Index30.855.0
Released—2026-07-08
WeightsOpenProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked1452

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

Category by category

Coding Grok 4.5 leads

Codellama 34b Instruct: 28.5 (#314), Grok 4.5: 52.2 (#35)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Coding10461474
DeepSWE—53.8%
FrontierCode—42.4%
LMArena WebDev—1553
SciCode—54.1%
WeirdML—46.4%
BigCodeBench Instruct29%—
BigCodeBench Complete37.1%—
ALE-Bench—1,309
HumanEval+43.9%—
MBPP+56.3%—

Agentic & Tool Use Not comparable

Codellama 34b Instruct: —, Grok 4.5: 44.4 (#17)

BenchmarkCodellama 34b InstructGrok 4.5
APEX-Agents—56.2%
τ²-bench Banking—47.9%
PostTrainBench—23.4%
GBAEval—65.4%
GDP.pdf—14%
LMArena Search—1213
Vending-Bench 2—3,887

Reasoning Grok 4.5 leads

Codellama 34b Instruct: 19.6 (#255), Grok 4.5: 56.1 (#25)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Hard Prompts10321462
ARC-AGI-2—52.6%
SimpleBench—70%
Kagi LLM Benchmark—83.5%
NYT Connections (extended)—79.9%
ARC-AGI-1—87.2%
CritPt—15.4%
Chess Puzzles—36%
DTBench—96.5%
LMCA—45.2%
Surface Evolver Bench—74.4%
Epoch Capabilities Index—153.92

Math Grok 4.5 leads

Codellama 34b Instruct: 31.0 (#230), Grok 4.5: 60.9 (#35)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Math10561459
FrontierMath (Tiers 1-3)—57.2%
FrontierMath Tier 4—24.4%
OTIS Mock AIME 2024-2025—97.8%
ProofBench—31%

Knowledge Not comparable

Codellama 34b Instruct: —, Grok 4.5: 62.3 (#24)

BenchmarkCodellama 34b InstructGrok 4.5
GPQA Diamond—93.4%
SimpleQA Verified—48.3%
LMArena Expert—1466

Multimodal Not comparable

Codellama 34b Instruct: —, Grok 4.5: 37.6 (#72)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Vision—1288
Blueprint-Bench 2—27.3%
Furniture Assembly—22.5%
LMArena Document—1452

Multilingual Grok 4.5 leads

Codellama 34b Instruct: 25.8 (#284), Grok 4.5: 54.4 (#42)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Non-English10111440
LMArena Chinese9761496
LMArena French—1456
LMArena German—1446
LMArena Japanese—1428
LMArena Korean—1404
LMArena Russian—1448
LMArena Spanish—1450

Instruction Following Grok 4.5 leads

Codellama 34b Instruct: 52.2 (#291), Grok 4.5: 76.0 (#48)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Instruction Following10281446

Long Context Grok 4.5 leads

Codellama 34b Instruct: 30.9 (#284), Grok 4.5: 44.8 (#56)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Longer Query10131463

Writing & Preference Grok 4.5 leads

Codellama 34b Instruct: 28.2 (#297), Grok 4.5: 65.8 (#42)

BenchmarkCodellama 34b InstructGrok 4.5
LMArena Text10661448
LMArena Creative Writing10321442
LMArena Multi-Turn10151456
EQ-Bench Creative Writing—1579

Frequently asked questions

Is Codellama 34b Instruct better than Grok 4.5?

Grok 4.5 is the stronger model overall, scoring 55.0 to 30.8 on the Noometry Index.

Is Codellama 34b Instruct or Grok 4.5 better for coding?

Grok 4.5 scores higher on coding benchmarks: 52.2 versus 28.5 in the Noometry coding category.

How many benchmarks do Codellama 34b Instruct and Grok 4.5 share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Grok 4.5 has 52.

Related comparisons

Go deeper