Noometry

Model comparison

Gemini 2.5 Pro vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 45.0 on the Noometry Index.

Last verified . 30 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 6 categories and Inkling-Small in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 42.7.
  • The biggest single-benchmark swing is ARC-AGI-1: 41% for Gemini 2.5 Pro and 84% for Inkling-Small.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 524K.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProInkling-Small
ProviderGoogleThinking Machines Lab
Noometry Index45.046.5
Released2025-03-252026-07-15
WeightsProprietaryOpen
Context window1.05M524K
Max output66K1.05M
Input $ / M tokens$1.25$0.45
Output $ / M tokens$10$1.20
Results tracked7833

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

Category by category

Coding Inkling-Small leads

Gemini 2.5 Pro: 42.4 (#101), Inkling-Small: 43.6 (#85)

BenchmarkGemini 2.5 ProInkling-Small
LMArena WebDev12271409
SciCode42.8%48.7%
LMArena Coding14521451
SWE-bench Verified57.6%—
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
GSO3.9%—
WeirdML54%—
LiveBench Coding85.9%—
CadEval64%—
ALE-Bench785.52—
AlgoTune1.51—

Agentic & Tool Use Not comparable

Gemini 2.5 Pro: 29.2 (#88), Inkling-Small: —

BenchmarkGemini 2.5 ProInkling-Small
Terminal-Bench32.6%—
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
LMArena Search1142—
METR Time Horizons55.4%—
Vending-Bench 2573.64—

Reasoning Inkling-Small leads

Gemini 2.5 Pro: 28.8 (#99), Inkling-Small: 38.6 (#63)

BenchmarkGemini 2.5 ProInkling-Small
ARC-AGI-24.9%40.1%
ARC-AGI-141%84%
CritPt2%8.3%
Chess Puzzles20%18%
LMArena Hard Prompts14551423
Epoch Capabilities Index145.32150.15
SimpleBench62.4%—
Kagi LLM Benchmark70.3%—
EnigmaEval5.6%—
LiveBench Reasoning89.8%—
Mystery Game Puzzles—6%
DTBench82.4%—
LiveBench Data Analysis79.9%—
LMCA34.8%—
ForecastBench61.3—
LiveBench82.3%—

Math Inkling-Small leads

Gemini 2.5 Pro: 32.5 (#213), Inkling-Small: 45.1 (#77)

BenchmarkGemini 2.5 ProInkling-Small
FrontierMath (Tiers 1-3)24.6%46.3%
FrontierMath Tier 40%17.1%
OTIS Mock AIME 2024-202584.7%90%
LMArena Math14501459
ProofBench—6%
Omni-MATH41.6%—
LiveBench Math90.2%—
MATH Level 595.9%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), Inkling-Small: 48.2 (#77)

BenchmarkGemini 2.5 ProInkling-Small
GPQA Diamond85.3%88.5%
LMArena Expert14521442
Humanity's Last Exam21.6%—
SimpleQA Verified—19.1%
MMLU-Pro86.3%—
Confabulations10.6%—
Vectara Hallucination Rate7%—
GPQA (HELM)74.9%—

Multimodal Gemini 2.5 Pro leads

Gemini 2.5 Pro: 45.2 (#18), Inkling-Small: 39.1 (#62)

BenchmarkGemini 2.5 ProInkling-Small
LMArena Vision12631235
GeoBench86%—
VPCT48%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), Inkling-Small: 51.7 (#104)

BenchmarkGemini 2.5 ProInkling-Small
LMArena Non-English14511402
LMArena Chinese15071465
LMArena French14721436
LMArena German14871405
LMArena Japanese14611405
LMArena Korean14341363
LMArena Russian14611391
LMArena Spanish14731428

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.0 (#75), Inkling-Small: 73.8 (#114)

BenchmarkGemini 2.5 ProInkling-Small
LMArena Instruction Following14371399
LiveBench Instruction Following80.6%—
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Inkling-Small: 42.7 (#118)

BenchmarkGemini 2.5 ProInkling-Small
LMArena Longer Query14491401
Fiction.LiveBench91.7%—

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), Inkling-Small: 59.6 (#107)

BenchmarkGemini 2.5 ProInkling-Small
LMArena Text14581414
LMArena Creative Writing14541331
EQ-Bench Creative Writing14211491
LMArena Multi-Turn14531418
Short-Story Creative Writing83.8%—
WildBench85.7%—
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 45.0 on the Noometry Index.

Which is cheaper, Gemini 2.5 Pro or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 524K.

How many benchmarks do Gemini 2.5 Pro and Inkling-Small share?

30 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper