Noometry

Model comparison

Claude 3 Sonnet vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 29.0 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Inkling-Small in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Inkling-Small leads 45.1 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 90% for Inkling-Small.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetInkling-Small
ProviderAnthropicThinking Machines Lab
Noometry Index29.046.5
Released2024-02-292026-07-15
WeightsProprietaryOpen
Context window—524K
Max output—1.05M
Input $ / M tokens—$0.45
Output $ / M tokens—$1.20
Results tracked3033

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

Category by category

Coding Inkling-Small leads

Claude 3 Sonnet: 29.6 (#302), Inkling-Small: 43.6 (#85)

BenchmarkClaude 3 SonnetInkling-Small
LMArena Coding12231451
LMArena WebDev—1409
SciCode—48.7%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Inkling-Small leads

Claude 3 Sonnet: 20.5 (#237), Inkling-Small: 38.6 (#63)

BenchmarkClaude 3 SonnetInkling-Small
LMArena Hard Prompts11971423
Epoch Capabilities Index120.7150.15
ARC-AGI-2—40.1%
ARC-AGI-1—84%
CritPt—8.3%
Chess Puzzles—18%
Mystery Game Puzzles—6%
DTBench53.6%—
WinoGrande75.1%—

Math Inkling-Small leads

Claude 3 Sonnet: 10.7 (#310), Inkling-Small: 45.1 (#77)

BenchmarkClaude 3 SonnetInkling-Small
OTIS Mock AIME 2024-20252.5%90%
LMArena Math12131459
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
ProofBench—6%
MATH Level 518.2%—

Knowledge Inkling-Small leads

Claude 3 Sonnet: 21.1 (#276), Inkling-Small: 48.2 (#77)

BenchmarkClaude 3 SonnetInkling-Small
GPQA Diamond40.6%88.5%
LMArena Expert11731442
SimpleQA Verified—19.1%
MMLU75.9%—

Multimodal Inkling-Small leads

Claude 3 Sonnet: 25.2 (#125), Inkling-Small: 39.1 (#62)

BenchmarkClaude 3 SonnetInkling-Small
LMArena Vision9841235

Multilingual Inkling-Small leads

Claude 3 Sonnet: 37.8 (#234), Inkling-Small: 51.7 (#104)

BenchmarkClaude 3 SonnetInkling-Small
LMArena Non-English12051402
LMArena Chinese11891465
LMArena French12291436
LMArena German12041405
LMArena Japanese11311405
LMArena Korean11281363
LMArena Russian12271391
LMArena Spanish12041428

Instruction Following Inkling-Small leads

Claude 3 Sonnet: 62.8 (#235), Inkling-Small: 73.8 (#114)

BenchmarkClaude 3 SonnetInkling-Small
LMArena Instruction Following11991399

Long Context Inkling-Small leads

Claude 3 Sonnet: 36.7 (#228), Inkling-Small: 42.7 (#118)

BenchmarkClaude 3 SonnetInkling-Small
LMArena Longer Query12111401

Writing & Preference Inkling-Small leads

Claude 3 Sonnet: 42.1 (#238), Inkling-Small: 59.6 (#107)

BenchmarkClaude 3 SonnetInkling-Small
LMArena Text12181414
LMArena Creative Writing11861331
LMArena Multi-Turn12271418
EQ-Bench Creative Writing—1491

Frequently asked questions

Is Claude 3 Sonnet better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Inkling-Small share?

21 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper