Noometry

Model comparison

Gemini 3.1 Pro Preview vs Inkling-Small

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 46.5 on the Noometry Index. Inkling-Small costs 7.1× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 33 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 7 categories and Inkling-Small in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 38.6.
  • The biggest single-benchmark swing is SimpleQA Verified: 73.5% for Gemini 3.1 Pro Preview and 19.1% for Inkling-Small.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview 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 Pro PreviewInkling-Small
ProviderGoogleThinking Machines Lab
Noometry Index56.746.5
Released2026-02-192026-07-15
WeightsProprietaryOpen
Context window1.05M524K
Max output66K1.05M
Input $ / M tokens$2$0.45
Output $ / M tokens$12$1.20
Results tracked7133

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

Category by category

Coding Inkling-Small leads

Gemini 3.1 Pro Preview: 42.5 (#99), Inkling-Small: 43.6 (#85)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
LMArena WebDev14471409
SciCode58.9%48.7%
LMArena Coding14841451
SWE-bench Verified75.6%—
DeepSWE11.7%—
GSO22.6%—
WeirdML72.1%—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Not comparable

Gemini 3.1 Pro Preview: 37.7 (#34), Inkling-Small: —

BenchmarkGemini 3.1 Pro PreviewInkling-Small
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Inkling-Small: 38.6 (#63)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
ARC-AGI-277.1%40.1%
ARC-AGI-198%84%
CritPt17.7%8.3%
Chess Puzzles55%18%
LMArena Hard Prompts14851423
Mystery Game Puzzles34%6%
Epoch Capabilities Index154.77150.15
SimpleBench79.6%—
NYT Connections (extended)97.4%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
DTBench97.1%—
LMCA53.8%—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Inkling-Small: 45.1 (#77)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
FrontierMath (Tiers 1-3)59.6%46.3%
FrontierMath Tier 426.8%17.1%
OTIS Mock AIME 2024-202595.6%90%
ProofBench26%6%
LMArena Math14851459
MathArena Final-Answer Competitions86.5%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Inkling-Small: 48.2 (#77)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
GPQA Diamond94.4%88.5%
SimpleQA Verified73.5%19.1%
LMArena Expert14851442
Humanity's Last Exam46.4%—
Vectara Hallucination Rate10.4%—

Multimodal Inkling-Small leads

Gemini 3.1 Pro Preview: 37.9 (#69), Inkling-Small: 39.1 (#62)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
LMArena Vision12961235
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Inkling-Small: 51.7 (#104)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
LMArena Non-English14771402
LMArena Chinese15291465
LMArena French14871436
LMArena German14911405
LMArena Japanese14931405
LMArena Korean14551363
LMArena Russian14981391
LMArena Spanish14791428

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Inkling-Small: 73.8 (#114)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
LMArena Instruction Following14661399

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Inkling-Small: 42.7 (#118)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
LMArena Longer Query14831401
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Inkling-Small: 59.6 (#107)

BenchmarkGemini 3.1 Pro PreviewInkling-Small
LMArena Text14811414
LMArena Creative Writing14821331
EQ-Bench Creative Writing14911491
LMArena Multi-Turn14881418
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Inkling-Small?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 46.5 on the Noometry Index. Inkling-Small costs 7.1× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 524K.

How many benchmarks do Gemini 3.1 Pro Preview and Inkling-Small share?

33 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper