Noometry

Model comparison

Inkling-Small vs Nova Premier 1.0

Inkling-Small is the stronger model overall, scoring 46.5 to 38.3 on the Noometry Index.

Last verified . 0 shared benchmarks.

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Nova Premier 1.0 Amazon

38.3

Rank #189 Confirmed

Summary

  • The widest gap is in reasoning, where Inkling-Small leads 38.6 to 23.0.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
  • Nova Premier 1.0 accepts more context: 1M tokens versus 524K.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Inkling-SmallNova Premier 1.0
ProviderThinking Machines LabAmazon
Noometry Index46.538.3
Released2026-07-152025-04-30
WeightsOpenProprietary
Context window524K1M
Max output1.05M10K
Input $ / M tokens$0.45$2.50
Output $ / M tokens$1.20$12.50
Results tracked336

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

Category by category

Coding Not comparable

Inkling-Small: 43.6 (#85), Nova Premier 1.0: —

BenchmarkInkling-SmallNova Premier 1.0
LMArena WebDev1409—
SciCode48.7%—
LMArena Coding1451—

Reasoning Inkling-Small leads

Inkling-Small: 38.6 (#63), Nova Premier 1.0: 23.0 (#185)

BenchmarkInkling-SmallNova Premier 1.0
ARC-AGI-240.1%—
Kagi LLM Benchmark—44.8%
ARC-AGI-184%—
CritPt8.3%—
Chess Puzzles18%—
LMArena Hard Prompts1423—
Mystery Game Puzzles6%—
Epoch Capabilities Index150.15—

Math Inkling-Small leads

Inkling-Small: 45.1 (#77), Nova Premier 1.0: 33.8 (#199)

BenchmarkInkling-SmallNova Premier 1.0
FrontierMath (Tiers 1-3)46.3%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202590%—
ProofBench6%—
Omni-MATH—35%
LMArena Math1459—

Knowledge Inkling-Small leads

Inkling-Small: 48.2 (#77), Nova Premier 1.0: 35.8 (#180)

BenchmarkInkling-SmallNova Premier 1.0
GPQA Diamond88.5%—
SimpleQA Verified19.1%—
MMLU-Pro—72.6%
GPQA (HELM)—51.8%
LMArena Expert1442—

Multimodal Not comparable

Inkling-Small: 39.1 (#62), Nova Premier 1.0: —

BenchmarkInkling-SmallNova Premier 1.0
LMArena Vision1235—

Multilingual Not comparable

Inkling-Small: 51.7 (#104), Nova Premier 1.0: —

BenchmarkInkling-SmallNova Premier 1.0
LMArena Non-English1402—
LMArena Chinese1465—
LMArena French1436—
LMArena German1405—
LMArena Japanese1405—
LMArena Korean1363—
LMArena Russian1391—
LMArena Spanish1428—

Instruction Following Inkling-Small leads

Inkling-Small: 73.8 (#114), Nova Premier 1.0: 66.8 (#204)

BenchmarkInkling-SmallNova Premier 1.0
IFEval—80.3%
LMArena Instruction Following1399—

Long Context Not comparable

Inkling-Small: 42.7 (#118), Nova Premier 1.0: —

BenchmarkInkling-SmallNova Premier 1.0
LMArena Longer Query1401—

Writing & Preference Inkling-Small leads

Inkling-Small: 59.6 (#107), Nova Premier 1.0: 51.0 (#178)

BenchmarkInkling-SmallNova Premier 1.0
LMArena Text1414—
LMArena Creative Writing1331—
EQ-Bench Creative Writing1491—
WildBench—78.8%
LMArena Multi-Turn1418—

Frequently asked questions

Is Inkling-Small better than Nova Premier 1.0?

Inkling-Small is the stronger model overall, scoring 46.5 to 38.3 on the Noometry Index.

Which is cheaper, Inkling-Small or Nova Premier 1.0?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.

Which has the bigger context window?

Nova Premier 1.0 does, with 1M tokens against 524K.

How many benchmarks do Inkling-Small and Nova Premier 1.0 share?

0 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper