Noometry

Model comparison

Inkling-Small vs Qwen2.5-Max

Inkling-Small is the stronger model overall, scoring 46.5 to 40.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Inkling-Small leads 38.6 to 25.6.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Inkling-SmallQwen2.5-Max
ProviderThinking Machines LabAlibaba (Qwen)
Noometry Index46.540.7
Released2026-07-152025-01-25
WeightsOpenProprietary
Context window524K—
Max output1.05M—
Input $ / M tokens$0.45—
Output $ / M tokens$1.20—
Results tracked3327

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

Category by category

Coding Inkling-Small leads

Inkling-Small: 43.6 (#85), Qwen2.5-Max: 41.8 (#117)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Coding14511359
LMArena WebDev1409—
SciCode48.7%—
LiveBench Coding—64.4%

Reasoning Inkling-Small leads

Inkling-Small: 38.6 (#63), Qwen2.5-Max: 25.6 (#147)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Hard Prompts14231360
Epoch Capabilities Index150.15132.53
ARC-AGI-240.1%—
ARC-AGI-184%—
CritPt8.3%—
Chess Puzzles18%—
LiveBench Reasoning—51.4%
Mystery Game Puzzles6%—
LiveBench Data Analysis—67.9%
LiveBench—62.3%

Math Inkling-Small leads

Inkling-Small: 45.1 (#77), Qwen2.5-Max: 36.9 (#162)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Math14591369
FrontierMath (Tiers 1-3)46.3%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202590%—
ProofBench6%—
LiveBench Math—58.4%

Knowledge Inkling-Small leads

Inkling-Small: 48.2 (#77), Qwen2.5-Max: 35.3 (#186)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Expert14421337
GPQA Diamond88.5%—
SimpleQA Verified19.1%—
Confabulations—21.8%

Multimodal Not comparable

Inkling-Small: 39.1 (#62), Qwen2.5-Max: —

BenchmarkInkling-SmallQwen2.5-Max
LMArena Vision1235—

Multilingual Inkling-Small leads

Inkling-Small: 51.7 (#104), Qwen2.5-Max: 48.1 (#146)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Non-English14021352
LMArena Chinese14651382
LMArena French14361396
LMArena German14051350
LMArena Japanese14051300
LMArena Korean13631304
LMArena Russian13911353
LMArena Spanish14281377

Instruction Following Inkling-Small leads

Inkling-Small: 73.8 (#114), Qwen2.5-Max: 71.3 (#152)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Instruction Following13991335
LiveBench Instruction Following—75.3%

Long Context Inkling-Small leads

Inkling-Small: 42.7 (#118), Qwen2.5-Max: 41.4 (#142)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Longer Query14011358

Writing & Preference Inkling-Small leads

Inkling-Small: 59.6 (#107), Qwen2.5-Max: 55.4 (#146)

BenchmarkInkling-SmallQwen2.5-Max
LMArena Text14141367
LMArena Creative Writing13311339
LMArena Multi-Turn14181364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing1491—
LiveBench Language—56.3%

Frequently asked questions

Is Inkling-Small better than Qwen2.5-Max?

Inkling-Small is the stronger model overall, scoring 46.5 to 40.7 on the Noometry Index.

Is Inkling-Small or Qwen2.5-Max better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 41.8 in the Noometry coding category.

How many benchmarks do Inkling-Small and Qwen2.5-Max share?

18 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper