Noometry

Model comparison

Inkling-Small vs Phi-4

Inkling-Small is the stronger model overall, scoring 46.5 to 31.2 on the Noometry Index. Phi-4 costs 7.3× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Inkling-Small leads 45.1 to 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 13.8% for Phi-4.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
  • Inkling-Small accepts more context: 524K tokens versus 128K.

Side by side

Inkling-SmallPhi-4
ProviderThinking Machines LabMicrosoft
Noometry Index46.531.2
Released2026-07-152024-12-11
WeightsOpenOpen
Context window524K128K
Max output1.05M4K
Input $ / M tokens$0.45$0.07
Output $ / M tokens$1.20$0.14
Results tracked3337

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

Category by category

Coding Inkling-Small leads

Inkling-Small: 43.6 (#85), Phi-4: 34.4 (#239)

BenchmarkInkling-SmallPhi-4
LMArena Coding14511231
LMArena WebDev1409—
SciCode48.7%—
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%

Agentic & Tool Use Not comparable

Inkling-Small: —, Phi-4: 22.8 (#128)

BenchmarkInkling-SmallPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Inkling-Small leads

Inkling-Small: 38.6 (#63), Phi-4: 17.7 (#291)

BenchmarkInkling-SmallPhi-4
Chess Puzzles18%1%
LMArena Hard Prompts14231220
Epoch Capabilities Index150.15130.42
ARC-AGI-240.1%—
ARC-AGI-184%—
CritPt8.3%—
LiveBench Reasoning—47.8%
Mystery Game Puzzles6%—
LiveBench Data Analysis—45.2%
LiveBench—41.6%

Math Inkling-Small leads

Inkling-Small: 45.1 (#77), Phi-4: 20.8 (#285)

BenchmarkInkling-SmallPhi-4
OTIS Mock AIME 2024-202590%13.8%
LMArena Math14591246
FrontierMath (Tiers 1-3)46.3%—
FrontierMath Tier 417.1%—
ProofBench6%—
LiveBench Math—42%
MATH Level 5—64.9%

Knowledge Inkling-Small leads

Inkling-Small: 48.2 (#77), Phi-4: 32.6 (#209)

BenchmarkInkling-SmallPhi-4
GPQA Diamond88.5%56.1%
LMArena Expert14421203
SimpleQA Verified19.1%—
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multimodal Not comparable

Inkling-Small: 39.1 (#62), Phi-4: —

BenchmarkInkling-SmallPhi-4
LMArena Vision1235—

Multilingual Inkling-Small leads

Inkling-Small: 51.7 (#104), Phi-4: 37.2 (#237)

BenchmarkInkling-SmallPhi-4
LMArena Non-English14021197
LMArena Chinese14651212
LMArena French14361224
LMArena German14051222
LMArena Japanese14051158
LMArena Korean13631151
LMArena Russian13911209
LMArena Spanish14281234

Instruction Following Inkling-Small leads

Inkling-Small: 73.8 (#114), Phi-4: 60.4 (#251)

BenchmarkInkling-SmallPhi-4
LMArena Instruction Following13991201
LiveBench Instruction Following—58.4%

Long Context Inkling-Small leads

Inkling-Small: 42.7 (#118), Phi-4: 36.9 (#226)

BenchmarkInkling-SmallPhi-4
LMArena Longer Query14011217

Writing & Preference Inkling-Small leads

Inkling-Small: 59.6 (#107), Phi-4: 40.5 (#244)

BenchmarkInkling-SmallPhi-4
LMArena Text14141217
LMArena Creative Writing13311182
LMArena Multi-Turn14181206
Short-Story Creative Writing—62.6%
EQ-Bench Creative Writing1491—
LiveBench Language—25.6%

Frequently asked questions

Is Inkling-Small better than Phi-4?

Inkling-Small is the stronger model overall, scoring 46.5 to 31.2 on the Noometry Index. Phi-4 costs 7.3× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

Which is cheaper, Inkling-Small or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

Is Inkling-Small or Phi-4 better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Inkling-Small does, with 524K tokens against 128K.

How many benchmarks do Inkling-Small and Phi-4 share?

21 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper