Noometry

Model comparison

Inkling-Small vs Kimi K2.7 Code

Inkling-Small is the stronger model overall, scoring 46.5 to 43.3 on the Noometry Index.

Last verified . 10 shared benchmarks.

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Inkling-Small scores higher in 1 category and Kimi K2.7 Code in 3 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.7 Code leads 52.9 to 45.1.
  • The biggest single-benchmark swing is SimpleQA Verified: 19.1% for Inkling-Small and 36.5% for Kimi K2.7 Code.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
  • Inkling-Small accepts more context: 524K tokens versus 262K.

Side by side

Inkling-SmallKimi K2.7 Code
ProviderThinking Machines LabMoonshot AI
Noometry Index46.543.3
Released2026-07-152026-06-12
WeightsOpenOpen
Context window524K262K
Max output1.05M262K
Input $ / M tokens$0.45$0.95
Output $ / M tokens$1.20$4
Results tracked3319

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

Category by category

Coding Too close to call

Inkling-Small: 43.6 (#85), Kimi K2.7 Code: 42.9 (#95)

BenchmarkInkling-SmallKimi K2.7 Code
LMArena WebDev14091473
SciCode48.7%47.5%
DeepSWE—30.5%
FrontierCode—30.1%
WeirdML—54.1%
LMArena Coding1451—
ALE-Bench—886.23

Agentic & Tool Use Not comparable

Inkling-Small: —, Kimi K2.7 Code: 24.0 (#122)

BenchmarkInkling-SmallKimi K2.7 Code
APEX-Agents—37.6%
GBAEval—0.9%
Vending-Bench 2—5,083

Reasoning Too close to call

Inkling-Small: 38.6 (#63), Kimi K2.7 Code: 39.0 (#61)

BenchmarkInkling-SmallKimi K2.7 Code
CritPt8.3%10%
Chess Puzzles18%21%
Epoch Capabilities Index150.15149.97
ARC-AGI-240.1%—
SimpleBench—57.9%
ARC-AGI-184%—
LMArena Hard Prompts1423—
Mystery Game Puzzles6%—
Surface Evolver Bench—48.8%

Math Kimi K2.7 Code leads

Inkling-Small: 45.1 (#77), Kimi K2.7 Code: 52.9 (#48)

BenchmarkInkling-SmallKimi K2.7 Code
FrontierMath (Tiers 1-3)46.3%54%
FrontierMath Tier 417.1%12.2%
OTIS Mock AIME 2024-202590%95.6%
ProofBench6%—
LMArena Math1459—

Knowledge Kimi K2.7 Code leads

Inkling-Small: 48.2 (#77), Kimi K2.7 Code: 53.5 (#57)

BenchmarkInkling-SmallKimi K2.7 Code
GPQA Diamond88.5%87.9%
SimpleQA Verified19.1%36.5%
LMArena Expert1442—

Multimodal Not comparable

Inkling-Small: 39.1 (#62), Kimi K2.7 Code: —

BenchmarkInkling-SmallKimi K2.7 Code
LMArena Vision1235—

Multilingual Not comparable

Inkling-Small: 51.7 (#104), Kimi K2.7 Code: —

BenchmarkInkling-SmallKimi K2.7 Code
LMArena Non-English1402—
LMArena Chinese1465—
LMArena French1436—
LMArena German1405—
LMArena Japanese1405—
LMArena Korean1363—
LMArena Russian1391—
LMArena Spanish1428—

Instruction Following Not comparable

Inkling-Small: 73.8 (#114), Kimi K2.7 Code: —

BenchmarkInkling-SmallKimi K2.7 Code
LMArena Instruction Following1399—

Long Context Not comparable

Inkling-Small: 42.7 (#118), Kimi K2.7 Code: —

BenchmarkInkling-SmallKimi K2.7 Code
LMArena Longer Query1401—

Writing & Preference Not comparable

Inkling-Small: 59.6 (#107), Kimi K2.7 Code: —

BenchmarkInkling-SmallKimi K2.7 Code
LMArena Text1414—
LMArena Creative Writing1331—
EQ-Bench Creative Writing1491—
LMArena Multi-Turn1418—

Frequently asked questions

Is Inkling-Small better than Kimi K2.7 Code?

Inkling-Small is the stronger model overall, scoring 46.5 to 43.3 on the Noometry Index.

Which is cheaper, Inkling-Small or Kimi K2.7 Code?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

Is Inkling-Small or Kimi K2.7 Code better for coding?

They score almost the same on coding (43.6 vs 42.9); test both on your own repository before choosing.

Which has the bigger context window?

Inkling-Small does, with 524K tokens against 262K.

How many benchmarks do Inkling-Small and Kimi K2.7 Code share?

10 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper