Noometry

Model comparison

Inkling-Small vs Llama 2-70B

Inkling-Small is the stronger model overall, scoring 46.5 to 24.4 on the Noometry Index.

Last verified . 20 shared benchmarks.

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Inkling-Small leads 48.2 to 7.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 0% for Llama 2-70B.

Side by side

Inkling-SmallLlama 2-70B
ProviderThinking Machines LabMeta
Noometry Index46.524.4
Released2026-07-152023-07-18
WeightsOpenOpen
Context window524K—
Max output1.05M—
Input $ / M tokens$0.45—
Output $ / M tokens$1.20—
Results tracked3335

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

Category by category

Coding Inkling-Small leads

Inkling-Small: 43.6 (#85), Llama 2-70B: 31.4 (#286)

BenchmarkInkling-SmallLlama 2-70B
LMArena Coding14511079
LMArena WebDev1409—
SciCode48.7%—

Reasoning Inkling-Small leads

Inkling-Small: 38.6 (#63), Llama 2-70B: 14.4 (#325)

BenchmarkInkling-SmallLlama 2-70B
LMArena Hard Prompts14231073
Epoch Capabilities Index150.15113.79
ARC-AGI-240.1%—
ARC-AGI-184%—
CritPt8.3%—
Chess Puzzles18%—
Mystery Game Puzzles6%—
DTBench—41.6%
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
PIQA—82.8%
WinoGrande—80.2%

Math Inkling-Small leads

Inkling-Small: 45.1 (#77), Llama 2-70B: 8.1 (#326)

BenchmarkInkling-SmallLlama 2-70B
OTIS Mock AIME 2024-202590%0%
LMArena Math14591091
FrontierMath (Tiers 1-3)46.3%—
FrontierMath Tier 417.1%—
ProofBench6%—
MATH Level 5—3.3%
GSM8K—69.6%

Knowledge Inkling-Small leads

Inkling-Small: 48.2 (#77), Llama 2-70B: 7.4 (#310)

BenchmarkInkling-SmallLlama 2-70B
GPQA Diamond88.5%26.3%
LMArena Expert14421039
SimpleQA Verified19.1%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
MMLU—69.9%
OpenBookQA—60.2%
TriviaQA—87.6%

Multimodal Not comparable

Inkling-Small: 39.1 (#62), Llama 2-70B: —

BenchmarkInkling-SmallLlama 2-70B
LMArena Vision1235—

Multilingual Inkling-Small leads

Inkling-Small: 51.7 (#104), Llama 2-70B: 27.7 (#274)

BenchmarkInkling-SmallLlama 2-70B
LMArena Non-English14021045
LMArena Chinese1465995
LMArena French14361090
LMArena German14051041
LMArena Japanese1405927
LMArena Korean1363964
LMArena Russian13911083
LMArena Spanish14281143

Instruction Following Inkling-Small leads

Inkling-Small: 73.8 (#114), Llama 2-70B: 54.9 (#278)

BenchmarkInkling-SmallLlama 2-70B
LMArena Instruction Following13991071

Long Context Inkling-Small leads

Inkling-Small: 42.7 (#118), Llama 2-70B: 32.3 (#270)

BenchmarkInkling-SmallLlama 2-70B
LMArena Longer Query14011062

Writing & Preference Inkling-Small leads

Inkling-Small: 59.6 (#107), Llama 2-70B: 32.3 (#279)

BenchmarkInkling-SmallLlama 2-70B
LMArena Text14141115
LMArena Creative Writing13311075
LMArena Multi-Turn14181088
EQ-Bench Creative Writing1491—

Frequently asked questions

Is Inkling-Small better than Llama 2-70B?

Inkling-Small is the stronger model overall, scoring 46.5 to 24.4 on the Noometry Index.

Is Inkling-Small or Llama 2-70B better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 31.4 in the Noometry coding category.

How many benchmarks do Inkling-Small and Llama 2-70B share?

20 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper