# ERNIE 5.1 vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 43.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 5 categories and Inkling-Small in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 20.9.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| Provider | Baidu | Thinking Machines Lab |
| Noometry Index | 43.1 | 46.5 |
| Rank | 87 | 57 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 43.4 (#78)
- Inkling-Small: 43.3 (#80)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Coding | 1488 | 1451 |
| LMArena WebDev | — | 1408 |
| SciCode | — | 48.7% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Inkling-Small: —

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- Inkling-Small: 39.0 (#53)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1424 |
| ARC-AGI-2 | — | 40.1% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.13 |

## Math

- ERNIE 5.1: 37.5 (#96)
- Inkling-Small: 44.9 (#65)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Math | 1481 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- Inkling-Small: 48.3 (#71)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Expert | 1491 | 1442 |
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |

## Multimodal

- ERNIE 5.1: —
- Inkling-Small: 38.4 (#59)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- Inkling-Small: 51.7 (#102)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1455 | 1400 |
| LMArena Chinese | 1507 | 1458 |
| LMArena French | 1486 | 1438 |
| LMArena German | 1470 | 1412 |
| LMArena Japanese | 1422 | 1399 |
| LMArena Korean | 1428 | 1355 |
| LMArena Russian | 1459 | 1392 |
| LMArena Spanish | 1472 | 1426 |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- Inkling-Small: 73.9 (#112)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1460 | 1397 |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- Inkling-Small: 42.7 (#113)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1462 | 1401 |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- Inkling-Small: 59.8 (#102)

| Benchmark | ERNIE 5.1 | Inkling-Small |
|---|---|---|
| LMArena Text | 1468 | 1413 |
| LMArena Creative Writing | 1440 | 1330 |
| LMArena Multi-Turn | 1471 | 1420 |
| EQ-Bench Creative Writing | — | 1491 |

## FAQ

### Is ERNIE 5.1 better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 43.1 on the Noometry Index.

### Is ERNIE 5.1 or Inkling-Small better for coding?

They score almost the same on coding (43.4 vs 43.3); test both on your own repository before choosing.

### How many benchmarks do ERNIE 5.1 and Inkling-Small share?

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Inkling-Small has 33.