Noometry

Model comparison

Claude 3 Haiku vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 25.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Haiku 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 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 90% for Inkling-Small.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuInkling-Small
ProviderAnthropicThinking Machines Lab
Noometry Index25.946.5
Released2024-03-072026-07-15
WeightsProprietaryOpen
Context window—524K
Max output—1.05M
Input $ / M tokens—$0.45
Output $ / M tokens—$1.20
Results tracked3733

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

Category by category

Coding Inkling-Small leads

Claude 3 Haiku: 26.4 (#325), Inkling-Small: 43.6 (#85)

BenchmarkClaude 3 HaikuInkling-Small
LMArena Coding11991451
LMArena WebDev—1409
SciCode—48.7%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Inkling-Small leads

Claude 3 Haiku: 16.3 (#307), Inkling-Small: 38.6 (#63)

BenchmarkClaude 3 HaikuInkling-Small
LMArena Hard Prompts11741423
Epoch Capabilities Index118.35150.15
ARC-AGI-2—40.1%
Kagi LLM Benchmark34.2%—
ARC-AGI-1—84%
CritPt—8.3%
Chess Puzzles—18%
Mystery Game Puzzles—6%
DTBench50.1%—
LMCA8.8%—
ForecastBench53.2—
WinoGrande74.2%—

Math Inkling-Small leads

Claude 3 Haiku: 9.8 (#319), Inkling-Small: 45.1 (#77)

BenchmarkClaude 3 HaikuInkling-Small
OTIS Mock AIME 2024-20251.8%90%
LMArena Math11881459
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
ProofBench—6%
MATH Level 514.9%—

Knowledge Inkling-Small leads

Claude 3 Haiku: 17.3 (#285), Inkling-Small: 48.2 (#77)

BenchmarkClaude 3 HaikuInkling-Small
GPQA Diamond36.3%88.5%
LMArena Expert11481442
SimpleQA Verified—19.1%
Confabulations34.2%—
MMLU73.8%—

Multimodal Inkling-Small leads

Claude 3 Haiku: 23.6 (#128), Inkling-Small: 39.1 (#62)

BenchmarkClaude 3 HaikuInkling-Small
LMArena Vision9501235
ScienceQA72%—

Multilingual Inkling-Small leads

Claude 3 Haiku: 36.0 (#243), Inkling-Small: 51.7 (#104)

BenchmarkClaude 3 HaikuInkling-Small
LMArena Non-English11781402
LMArena Chinese11551465
LMArena French11951436
LMArena German11741405
LMArena Japanese11021405
LMArena Korean11091363
LMArena Russian12041391
LMArena Spanish11661428

Instruction Following Inkling-Small leads

Claude 3 Haiku: 61.3 (#247), Inkling-Small: 73.8 (#114)

BenchmarkClaude 3 HaikuInkling-Small
LMArena Instruction Following11731399

Long Context Inkling-Small leads

Claude 3 Haiku: 36.1 (#237), Inkling-Small: 42.7 (#118)

BenchmarkClaude 3 HaikuInkling-Small
LMArena Longer Query11901401

Writing & Preference Inkling-Small leads

Claude 3 Haiku: 29.7 (#291), Inkling-Small: 59.6 (#107)

BenchmarkClaude 3 HaikuInkling-Small
LMArena Text11951414
LMArena Creative Writing11571331
EQ-Bench Creative Writing7171491
LMArena Multi-Turn11901418

Frequently asked questions

Is Claude 3 Haiku better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 25.9 on the Noometry Index.

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

Inkling-Small scores higher on coding benchmarks: 43.6 versus 26.4 in the Noometry coding category.

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

22 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper