Noometry

Model comparison

Codellama 34b Instruct vs GPT-4.1 nano

Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 27.9 on the Noometry Index.

Last verified . 10 shared benchmarks.

Codellama 34b Instruct Meta

30.8

Rank #287 Confirmed

GPT-4.1 nano OpenAI

27.9

Rank #327 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 4 categories and GPT-4.1 nano in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where GPT-4.1 nano leads 41.6 to 25.8.
  • Codellama 34b Instruct has downloadable open weights; the other is API-only.

Side by side

Codellama 34b InstructGPT-4.1 nano
ProviderMetaOpenAI
Noometry Index30.827.9
Released—2025-04-14
WeightsOpenProprietary
Context window—1.05M
Max output—33K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.40
Results tracked1438

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

Category by category

Coding Codellama 34b Instruct leads

Codellama 34b Instruct: 28.5 (#314), GPT-4.1 nano: 24.1 (#330)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Coding10461306
Aider Polyglot—8.9%
SciCode—25.9%
WeirdML—19%
BigCodeBench Instruct29%—
BigCodeBench Complete37.1%—
HumanEval+43.9%—
MBPP+56.3%—

Agentic & Tool Use Not comparable

Codellama 34b Instruct: —, GPT-4.1 nano: 26.5 (#104)

BenchmarkCodellama 34b InstructGPT-4.1 nano
Berkeley Function Calling Leaderboard—33%

Reasoning Codellama 34b Instruct leads

Codellama 34b Instruct: 19.6 (#255), GPT-4.1 nano: 8.5 (#349)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Hard Prompts10321286
ARC-AGI-2—0%
Kagi LLM Benchmark—33.3%
ARC-AGI-1—0%
CritPt—0%
DTBench—52.5%
LMCA—5.5%
Epoch Capabilities Index—129.62

Math Codellama 34b Instruct leads

Codellama 34b Instruct: 31.0 (#230), GPT-4.1 nano: 26.9 (#252)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Math10561274
OTIS Mock AIME 2024-2025—28.9%
Omni-MATH—36.7%
MATH Level 5—70%
FrontierMath (Feb 2025 set)—1%

Knowledge Not comparable

Codellama 34b Instruct: —, GPT-4.1 nano: 21.8 (#273)

BenchmarkCodellama 34b InstructGPT-4.1 nano
GPQA Diamond—48.9%
SimpleQA Verified—6%
MMLU-Pro—55%
GPQA (HELM)—50.7%
LMArena Expert—1272

Multimodal Not comparable

Codellama 34b Instruct: —, GPT-4.1 nano: 29.2 (#113)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Vision—1063

Multilingual GPT-4.1 nano leads

Codellama 34b Instruct: 25.8 (#284), GPT-4.1 nano: 41.6 (#205)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Non-English10111260
LMArena Chinese9761270
LMArena German—1288
LMArena Japanese—1198
LMArena Russian—1261

Instruction Following GPT-4.1 nano leads

Codellama 34b Instruct: 52.2 (#291), GPT-4.1 nano: 67.8 (#193)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Instruction Following10281267
IFEval—84.3%

Long Context Codellama 34b Instruct leads

Codellama 34b Instruct: 30.9 (#284), GPT-4.1 nano: 23.7 (#296)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Longer Query10131283
Fiction.LiveBench—25%

Writing & Preference GPT-4.1 nano leads

Codellama 34b Instruct: 28.2 (#297), GPT-4.1 nano: 40.5 (#243)

BenchmarkCodellama 34b InstructGPT-4.1 nano
LMArena Text10661285
LMArena Creative Writing10321260
LMArena Multi-Turn10151277
EQ-Bench Creative Writing—946
WildBench—81.2%

Frequently asked questions

Is Codellama 34b Instruct better than GPT-4.1 nano?

Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 27.9 on the Noometry Index.

Is Codellama 34b Instruct or GPT-4.1 nano better for coding?

Codellama 34b Instruct scores higher on coding benchmarks: 28.5 versus 24.1 in the Noometry coding category.

How many benchmarks do Codellama 34b Instruct and GPT-4.1 nano share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GPT-4.1 nano has 38.

Related comparisons

Go deeper