Noometry

Model comparison

Gemini 3.1 Flash Lite vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 40.4 on the Noometry Index.

Last verified . 26 shared benchmarks.

Gemini 3.1 Flash Lite Google

40.4

Rank #141 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #57 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 3 categories and Inkling-Small in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Inkling-Small leads 39.0 to 22.3.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 27.7% for Gemini 3.1 Flash Lite and 46.3% for Inkling-Small.
  • Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
  • Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 524K.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Flash LiteInkling-Small
ProviderGoogleThinking Machines Lab
Noometry Index40.446.5
Released2026-03-032026-07-15
WeightsProprietaryOpen
Context window1.05M524K
Max output66K1.05M
Input $ / M tokens$0.25$0.45
Output $ / M tokens$1.50$1.20
Results tracked3833

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

Category by category

Coding Inkling-Small leads

Gemini 3.1 Flash Lite: 37.5 (#179), Inkling-Small: 43.3 (#80)

BenchmarkGemini 3.1 Flash LiteInkling-Small
LMArena WebDev12561408
SciCode41.9%48.7%
LMArena Coding14001451
WeirdML52.2%—
ALE-Bench797.73—

Agentic & Tool Use Not comparable

Gemini 3.1 Flash Lite: 29.9 (#72), Inkling-Small: —

BenchmarkGemini 3.1 Flash LiteInkling-Small
DeepResearch Bench37.3%—

Reasoning Inkling-Small leads

Gemini 3.1 Flash Lite: 22.3 (#181), Inkling-Small: 39.0 (#53)

BenchmarkGemini 3.1 Flash LiteInkling-Small
CritPt1.1%8.3%
Chess Puzzles25%18%
LMArena Hard Prompts14071424
Epoch Capabilities Index144.45150.13
ARC-AGI-2—40.1%
Kagi LLM Benchmark67.2%—
NYT Connections (extended)8.2%—
ARC-AGI-1—84%
EnigmaEval3%—
Thematic Generalization63.3%—
Mystery Game Puzzles—6%
DTBench76.8%—
LMCA35%—
ForecastBench54.4—

Math Inkling-Small leads

Gemini 3.1 Flash Lite: 39.5 (#82), Inkling-Small: 44.9 (#65)

BenchmarkGemini 3.1 Flash LiteInkling-Small
FrontierMath (Tiers 1-3)27.7%46.3%
OTIS Mock AIME 2024-202580%90%
LMArena Math14271453
FrontierMath Tier 4—17.1%
ProofBench—6%

Knowledge Inkling-Small leads

Gemini 3.1 Flash Lite: 41.7 (#95), Inkling-Small: 48.3 (#71)

BenchmarkGemini 3.1 Flash LiteInkling-Small
GPQA Diamond81.8%88.5%
LMArena Expert13971442
Humanity's Last Exam8.6%—
SimpleQA Verified—19.1%
Vectara Hallucination Rate8.2%—

Multimodal Too close to call

Gemini 3.1 Flash Lite: 38.7 (#57), Inkling-Small: 38.4 (#59)

BenchmarkGemini 3.1 Flash LiteInkling-Small
LMArena Vision12401235

Multilingual Too close to call

Gemini 3.1 Flash Lite: 52.5 (#82), Inkling-Small: 51.7 (#102)

BenchmarkGemini 3.1 Flash LiteInkling-Small
LMArena Non-English14101400
LMArena Chinese14611458
LMArena French14231438
LMArena German14291412
LMArena Japanese14111399
LMArena Korean13931355
LMArena Russian14201392
LMArena Spanish14201426

Instruction Following Inkling-Small leads

Gemini 3.1 Flash Lite: 72.9 (#126), Inkling-Small: 73.9 (#112)

BenchmarkGemini 3.1 Flash LiteInkling-Small
LMArena Instruction Following13761397

Long Context Too close to call

Gemini 3.1 Flash Lite: 42.5 (#117), Inkling-Small: 42.7 (#113)

BenchmarkGemini 3.1 Flash LiteInkling-Small
LMArena Longer Query13941401

Writing & Preference Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 61.0 (#90), Inkling-Small: 59.8 (#102)

BenchmarkGemini 3.1 Flash LiteInkling-Small
LMArena Text14161413
LMArena Creative Writing14011330
LMArena Multi-Turn14171420
EQ-Bench Creative Writing—1491

Frequently asked questions

Is Gemini 3.1 Flash Lite better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 40.4 on the Noometry Index.

Which is cheaper, Gemini 3.1 Flash Lite or Inkling-Small?

Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

Is Gemini 3.1 Flash Lite or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 37.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 524K.

How many benchmarks do Gemini 3.1 Flash Lite and Inkling-Small share?

26 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper