Noometry

Model comparison

Codellama 34b Instruct vs Inkling

Inkling is the stronger model overall, scoring 44.1 to 30.2 on the Noometry Index.

Last verified . 10 shared benchmarks.

Codellama 34b Instruct Meta

30.2

Rank #285 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #75 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and Inkling in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Inkling leads 65.5 to 28.4.

Side by side

Codellama 34b InstructInkling
ProviderMetaThinking Machines Lab
Noometry Index30.244.1
Released—2026-07-15
WeightsOpenOpen
Context window—66K
Max output—66K
Input $ / M tokens—$1.87
Output $ / M tokens—$4.68
Results tracked1441

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

Category by category

Coding Inkling leads

Codellama 34b Instruct: 28.0 (#310), Inkling: 34.1 (#229)

BenchmarkCodellama 34b InstructInkling
LMArena Coding10461463
FrontierCode—14%
LMArena WebDev—1412
FrontierSWE—4.1%
SciCode—47%
WeirdML—32.3%
BigCodeBench Instruct29%—
BigCodeBench Complete37.1%—
ALE-Bench—946
HumanEval+43.9%—
MBPP+56.3%—

Agentic & Tool Use Not comparable

Codellama 34b Instruct: —, Inkling: 29.5 (#76)

BenchmarkCodellama 34b InstructInkling
APEX-Agents—33.8%
τ²-bench Banking—25%

Reasoning Inkling leads

Codellama 34b Instruct: 18.8 (#250), Inkling: 40.6 (#48)

BenchmarkCodellama 34b InstructInkling
LMArena Hard Prompts10321452
ARC-AGI-2—36.5%
SimpleBench—50%
ARC-AGI-1—79.5%
CritPt—5.4%
Chess Puzzles—21%
DTBench—87.5%
LMCA—37.6%
Epoch Capabilities Index—148.6

Math Inkling leads

Codellama 34b Instruct: 28.5 (#227), Inkling: 31.2 (#198)

BenchmarkCodellama 34b InstructInkling
LMArena Math10561482
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
OTIS Mock AIME 2024-2025—88.9%
ProofBench—0%

Knowledge Not comparable

Codellama 34b Instruct: —, Inkling: 55.2 (#44)

BenchmarkCodellama 34b InstructInkling
GPQA Diamond—88.3%
SimpleQA Verified—40.3%
LMArena Expert—1468

Multilingual Inkling leads

Codellama 34b Instruct: 25.9 (#279), Inkling: 54.2 (#49)

BenchmarkCodellama 34b InstructInkling
LMArena Non-English10111434
LMArena Chinese9761495
LMArena French—1453
LMArena German—1456
LMArena Japanese—1428
LMArena Korean—1401
LMArena Russian—1430
LMArena Spanish—1442

Instruction Following Inkling leads

Codellama 34b Instruct: 52.4 (#286), Inkling: 75.3 (#65)

BenchmarkCodellama 34b InstructInkling
LMArena Instruction Following10281427

Long Context Inkling leads

Codellama 34b Instruct: 30.8 (#279), Inkling: 43.9 (#79)

BenchmarkCodellama 34b InstructInkling
LMArena Longer Query10141436

Writing & Preference Inkling leads

Codellama 34b Instruct: 28.4 (#292), Inkling: 65.5 (#48)

BenchmarkCodellama 34b InstructInkling
LMArena Text10661443
LMArena Creative Writing10321390
LMArena Multi-Turn10151436
EQ-Bench Creative Writing—1611
EQ-Bench 4—1226

Frequently asked questions

Is Codellama 34b Instruct better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 30.2 on the Noometry Index.

Is Codellama 34b Instruct or Inkling better for coding?

Inkling scores higher on coding benchmarks: 34.1 versus 28.0 in the Noometry coding category.

How many benchmarks do Codellama 34b Instruct and Inkling share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper