# Amazon Nova Experimental Chat 10 20 vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 41.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-10-20-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Amazon Nova Experimental Chat 10 20 scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 27.3.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| Provider | Amazon | Thinking Machines Lab |
| Noometry Index | 41.5 | 46.5 |
| Rank | 122 | 57 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Experimental Chat 10 20: 41.0 (#123)
- Inkling-Small: 43.3 (#80)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Coding | 1413 | 1451 |
| LMArena WebDev | — | 1408 |
| SciCode | — | 48.7% |

## Reasoning

- Amazon Nova Experimental Chat 10 20: 27.3 (#110)
- Inkling-Small: 39.0 (#53)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1424 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.13 |

## Math

- Amazon Nova Experimental Chat 10 20: 36.2 (#121)
- Inkling-Small: 44.9 (#65)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Math | 1425 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |

## Knowledge

- Amazon Nova Experimental Chat 10 20: 37.8 (#142)
- Inkling-Small: 48.3 (#71)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Expert | 1385 | 1442 |
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |

## Multimodal

- Amazon Nova Experimental Chat 10 20: —
- Inkling-Small: 38.4 (#59)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |

## Multilingual

- Amazon Nova Experimental Chat 10 20: 49.7 (#127)
- Inkling-Small: 51.7 (#102)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1372 | 1400 |
| LMArena Chinese | 1405 | 1458 |
| LMArena French | 1426 | 1438 |
| LMArena German | 1391 | 1412 |
| LMArena Japanese | 1355 | 1399 |
| LMArena Korean | 1327 | 1355 |
| LMArena Russian | 1371 | 1392 |
| LMArena Spanish | 1381 | 1426 |

## Instruction Following

- Amazon Nova Experimental Chat 10 20: 72.3 (#136)
- Inkling-Small: 73.9 (#112)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1365 | 1397 |

## Long Context

- Amazon Nova Experimental Chat 10 20: 41.7 (#128)
- Inkling-Small: 42.7 (#113)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1370 | 1401 |

## Writing & Preference

- Amazon Nova Experimental Chat 10 20: 56.9 (#131)
- Inkling-Small: 59.8 (#102)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Inkling-Small |
|---|---|---|
| LMArena Text | 1394 | 1413 |
| LMArena Creative Writing | 1318 | 1330 |
| LMArena Multi-Turn | 1364 | 1420 |
| EQ-Bench Creative Writing | — | 1491 |

## FAQ

### Is Amazon Nova Experimental Chat 10 20 better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 41.5 on the Noometry Index.

### Is Amazon Nova Experimental Chat 10 20 or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 41.0 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 10 20 and Inkling-Small share?

17 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and Inkling-Small has 33.