Model comparison

Inkling-Small vs Nemotron 4 340b Instruct

Inkling-Small is the stronger model overall, scoring 46.5 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Nemotron 4 340b Instruct NVIDIA

35.9

Rank #223 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Nemotron 4 340b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Inkling-Small leads 59.6 to 42.7.

Side by side

Inkling-Small and Nemotron 4 340b Instruct specifications
Inkling-SmallNemotron 4 340b Instruct
ProviderThinking Machines LabNVIDIA
Noometry Index46.535.9
Released2026-07-152024-06-14
WeightsOpenOpen
Context window524K—
Max output1.05M—
Input $ / M tokens$0.45—
Output $ / M tokens$1.20—
Results tracked3317

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

Category by category

Coding Inkling-Small leads

Inkling-Small: 43.6 (#85), Nemotron 4 340b Instruct: 35.2 (#228)

Coding benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Coding14511209
LMArena WebDev1409—
SciCode48.7%—

Reasoning Inkling-Small leads

Inkling-Small: 38.6 (#63), Nemotron 4 340b Instruct: 23.4 (#178)

Reasoning benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Hard Prompts14231202
ARC-AGI-240.1%—
ARC-AGI-184%—
CritPt8.3%—
Chess Puzzles18%—
Mystery Game Puzzles6%—
Epoch Capabilities Index150.15—

Math Inkling-Small leads

Inkling-Small: 45.1 (#77), Nemotron 4 340b Instruct: 34.3 (#195)

Math benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Math14591216
FrontierMath (Tiers 1-3)46.3%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202590%—
ProofBench6%—

Knowledge Inkling-Small leads

Inkling-Small: 48.2 (#77), Nemotron 4 340b Instruct: 32.0 (#216)

Knowledge benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Expert14421171
GPQA Diamond88.5%—
SimpleQA Verified19.1%—

Multimodal Not comparable

Inkling-Small: 39.1 (#62), Nemotron 4 340b Instruct: —

Multimodal benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Vision1235—

Multilingual Inkling-Small leads

Inkling-Small: 51.7 (#104), Nemotron 4 340b Instruct: 37.9 (#233)

Multilingual benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Non-English14021206
LMArena Chinese14651214
LMArena French14361197
LMArena German14051192
LMArena Japanese14051128
LMArena Korean13631148
LMArena Russian13911219
LMArena Spanish14281195

Instruction Following Inkling-Small leads

Inkling-Small: 73.8 (#114), Nemotron 4 340b Instruct: 63.1 (#232)

Instruction Following benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Instruction Following13991203

Long Context Inkling-Small leads

Inkling-Small: 42.7 (#118), Nemotron 4 340b Instruct: 37.1 (#221)

Long Context benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Longer Query14011225

Writing & Preference Inkling-Small leads

Inkling-Small: 59.6 (#107), Nemotron 4 340b Instruct: 42.7 (#233)

Writing & Preference benchmarks
BenchmarkInkling-SmallNemotron 4 340b Instruct
LMArena Text14141225
LMArena Creative Writing13311203
LMArena Multi-Turn14181214
EQ-Bench Creative Writing1491—

Frequently asked questions

Is Inkling-Small better than Nemotron 4 340b Instruct?

Inkling-Small is the stronger model overall, scoring 46.5 to 35.9 on the Noometry Index.

Is Inkling-Small or Nemotron 4 340b Instruct better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 35.2 in the Noometry coding category.

How many benchmarks do Inkling-Small and Nemotron 4 340b Instruct share?

17 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Nemotron 4 340b Instruct has 17.

Related comparisons

Go deeper