Model comparison

DeepSeek Coder 1.3B vs Inkling-Small

Inkling-Small has enough public results to be ranked (#57); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

DeepSeek Coder 1.3B DeepSeek

34.5

Unranked Sparse

Inkling-Small Thinking Machines Lab

46.5

Rank #57 Confirmed

Summary

  • They share 1 benchmark with published results for both. DeepSeek Coder 1.3B scores higher in 0 categories and Inkling-Small in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where Inkling-Small leads 43.3 to 30.7.

Side by side

DeepSeek Coder 1.3B and Inkling-Small specifications
DeepSeek Coder 1.3BInkling-Small
ProviderDeepSeekThinking Machines Lab
Noometry Index34.546.5
Released2023-11-022026-07-15
WeightsOpenOpen
Context window—524K
Max output—1.05M
Input $ / M tokens—$0.45
Output $ / M tokens—$1.20
Results tracked933

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

Category by category

Coding Inkling-Small leads

DeepSeek Coder 1.3B: 30.7 (#282), Inkling-Small: 43.3 (#80)

Coding benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
LMArena WebDev—1408
SciCode—48.7%
BigCodeBench Instruct22.8%—
LMArena Coding—1451
BigCodeBench Complete29.6%—
HumanEval+60.4%—
MBPP+54.8%—

Reasoning Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 39.0 (#53)

Reasoning benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
Epoch Capabilities Index62.18150.13
ARC-AGI-2—40.1%
ARC-AGI-1—84%
CritPt—8.3%
Chess Puzzles—18%
LMArena Hard Prompts—1424
Mystery Game Puzzles—6%
WinoGrande53.3%—

Math Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 44.9 (#65)

Math benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
OTIS Mock AIME 2024-2025—90%
ProofBench—6%
LMArena Math—1453
GSM8K4.4%—

Knowledge Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 48.3 (#71)

Knowledge benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
GPQA Diamond—88.5%
SimpleQA Verified—19.1%
LMArena Expert—1442
ARC (AI2) Challenge25.4%—
MMLU25.8%—

Multimodal Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 38.4 (#59)

Multimodal benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
LMArena Vision—1235

Multilingual Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 51.7 (#102)

Multilingual benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
LMArena Non-English—1400
LMArena Chinese—1458
LMArena French—1438
LMArena German—1412
LMArena Japanese—1399
LMArena Korean—1355
LMArena Russian—1392
LMArena Spanish—1426

Instruction Following Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 73.9 (#112)

Instruction Following benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
LMArena Instruction Following—1397

Long Context Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 42.7 (#113)

Long Context benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
LMArena Longer Query—1401

Writing & Preference Not comparable

DeepSeek Coder 1.3B: —, Inkling-Small: 59.8 (#102)

Writing & Preference benchmarks
BenchmarkDeepSeek Coder 1.3BInkling-Small
LMArena Text—1413
LMArena Creative Writing—1330
EQ-Bench Creative Writing—1491
LMArena Multi-Turn—1420

Frequently asked questions

Is DeepSeek Coder 1.3B better than Inkling-Small?

Inkling-Small has enough public results to be ranked (#57); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 1.3B or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 30.7 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 1.3B and Inkling-Small share?

1 benchmark has published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper