Model comparison
Amazon Nova Lite vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 31.9 on the Noometry Index. Amazon Nova Lite costs 6.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Amazon Nova Lite scores higher in 0 categories and Inkling-Small in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.2 to 26.3.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 300K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Inkling-Small | |
|---|---|---|
| Provider | Amazon | Thinking Machines Lab |
| Noometry Index | 31.9 | 46.5 |
| Released | 2024-12-03 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 300K | 524K |
| Max output | 10K | 1.05M |
| Input $ / M tokens | $0.06 | $0.45 |
| Output $ / M tokens | $0.24 | $1.20 |
| Results tracked | 34 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Amazon Nova Lite: 32.5 (#270), Inkling-Small: 43.6 (#85)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Coding | 1239 | 1451 |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| LiveBench Coding | 27.5% | — |
| ALE-Bench | 236.25 | — |
Reasoning Inkling-Small leads
Amazon Nova Lite: 19.3 (#260), Inkling-Small: 38.6 (#63)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1423 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| LiveBench Reasoning | 36.7% | — |
| Mystery Game Puzzles | — | 6% |
| LiveBench Data Analysis | 37.2% | — |
| Epoch Capabilities Index | — | 150.15 |
| LiveBench | 36.4% | — |
Math Inkling-Small leads
Amazon Nova Lite: 27.8 (#247), Inkling-Small: 45.1 (#77)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Math | 1227 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
Knowledge Inkling-Small leads
Amazon Nova Lite: 26.3 (#259), Inkling-Small: 48.2 (#77)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Expert | 1201 | 1442 |
| GPQA Diamond | — | 88.5% |
| Humanity's Last Exam | 3.6% | — |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |
Multimodal Inkling-Small leads
Amazon Nova Lite: 25.5 (#123), Inkling-Small: 39.1 (#62)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Vision | 990 | 1235 |
Multilingual Inkling-Small leads
Amazon Nova Lite: 38.0 (#232), Inkling-Small: 51.7 (#104)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1208 | 1402 |
| LMArena Chinese | 1225 | 1465 |
| LMArena French | 1237 | 1436 |
| LMArena German | 1229 | 1405 |
| LMArena Japanese | 1153 | 1405 |
| LMArena Korean | 1153 | 1363 |
| LMArena Russian | 1216 | 1391 |
| LMArena Spanish | 1226 | 1428 |
Instruction Following Inkling-Small leads
Amazon Nova Lite: 59.3 (#255), Inkling-Small: 73.8 (#114)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1205 | 1399 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Inkling-Small leads
Amazon Nova Lite: 37.4 (#217), Inkling-Small: 42.7 (#118)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1234 | 1401 |
Writing & Preference Inkling-Small leads
Amazon Nova Lite: 42.1 (#237), Inkling-Small: 59.6 (#107)
| Benchmark | Amazon Nova Lite | Inkling-Small |
|---|---|---|
| LMArena Text | 1229 | 1414 |
| LMArena Creative Writing | 1197 | 1331 |
| LMArena Multi-Turn | 1199 | 1418 |
| EQ-Bench Creative Writing | — | 1491 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 31.9 on the Noometry Index. Amazon Nova Lite costs 6.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Lite or Inkling-Small?
Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Amazon Nova Lite or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 32.5 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 300K.
How many benchmarks do Amazon Nova Lite and Inkling-Small share?
18 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Inkling-Small has 33.