Model comparison

Gemma 2 9B vs Inkling

Inkling is the stronger model overall, scoring 44.1 to 25.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Inkling in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Inkling leads 55.1 to 9.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 88.9% for Inkling.

Side by side

Gemma 2 9B and Inkling specifications
Gemma 2 9BInkling
ProviderGoogleThinking Machines Lab
Noometry Index25.944.1
Released2024-06-242026-07-15
WeightsOpenOpen
Context window—66K
Max output—66K
Input $ / M tokens—$1.87
Output $ / M tokens—$4.68
Results tracked3541

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

Category by category

Coding Inkling leads

Gemma 2 9B: 29.4 (#304), Inkling: 34.5 (#234)

Coding benchmarks
BenchmarkGemma 2 9BInkling
LMArena Coding11731464
FrontierCode—14%
LMArena WebDev—1413
FrontierSWE—4.1%
SciCode—47%
WeirdML—32.3%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
ALE-Bench—946

Agentic & Tool Use Not comparable

Gemma 2 9B: —, Inkling: 29.6 (#85)

Agentic & Tool Use benchmarks
BenchmarkGemma 2 9BInkling
APEX-Agents—33.8%
τ²-bench Banking—25%

Reasoning Inkling leads

Gemma 2 9B: 15.9 (#309), Inkling: 40.4 (#56)

Reasoning benchmarks
BenchmarkGemma 2 9BInkling
LMArena Hard Prompts11711451
Epoch Capabilities Index119.83148.54
ARC-AGI-2—36.5%
SimpleBench—50%
ARC-AGI-1—79.5%
CritPt—5.4%
Chess Puzzles—21%
LiveBench Reasoning15.2%—
DTBench—87.5%
LiveBench Data Analysis36.4%—
LMCA—37.6%
LiveBench28.7%—
PIQA83.7%—

Math Inkling leads

Gemma 2 9B: 9.9 (#318), Inkling: 31.3 (#225)

Math benchmarks
BenchmarkGemma 2 9BInkling
OTIS Mock AIME 2024-20250.6%88.9%
LMArena Math11831479
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
ProofBench—0%
LiveBench Math19.8%—
MATH Level 521%—
GSM8K84.9%—

Knowledge Inkling leads

Gemma 2 9B: 9.7 (#305), Inkling: 55.1 (#49)

Knowledge benchmarks
BenchmarkGemma 2 9BInkling
GPQA Diamond27.5%88.3%
LMArena Expert11471465
SimpleQA Verified—40.3%
BoolQ85.7%—
MMLU72.1%—

Multilingual Inkling leads

Gemma 2 9B: 36.6 (#238), Inkling: 54.0 (#52)

Multilingual benchmarks
BenchmarkGemma 2 9BInkling
LMArena Non-English11881434
LMArena Chinese11851490
LMArena French11901458
LMArena German11861446
LMArena Japanese11441429
LMArena Korean11371404
LMArena Russian12001429
LMArena Spanish12001448

Instruction Following Inkling leads

Gemma 2 9B: 57.6 (#269), Inkling: 75.1 (#71)

Instruction Following benchmarks
BenchmarkGemma 2 9BInkling
LMArena Instruction Following11781426
LiveBench Instruction Following52.6%—

Long Context Inkling leads

Gemma 2 9B: 36.3 (#233), Inkling: 43.8 (#86)

Long Context benchmarks
BenchmarkGemma 2 9BInkling
LMArena Longer Query11971434

Writing & Preference Inkling leads

Gemma 2 9B: 32.1 (#281), Inkling: 65.2 (#51)

Writing & Preference benchmarks
BenchmarkGemma 2 9BInkling
LMArena Text12071441
LMArena Creative Writing12061387
EQ-Bench Creative Writing8411611
LMArena Multi-Turn11931436
EQ-Bench 4—1226
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Inkling better for coding?

Inkling scores higher on coding benchmarks: 34.5 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Inkling share?

21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper