# Inkling-Small vs Qwen2-72B

> Inkling-Small is the stronger model overall, scoring 46.5 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-small-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.3 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 88.5% for Inkling-Small and 40.8% for Qwen2-72B.

## Snapshot

| | Inkling-Small | Qwen2-72B |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 29.5 |
| Rank | 57 | 294 |
| Context | 524K | — |
| Input $/M | $0.45 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.3 (#80)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1451 | 1196 |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Inkling-Small: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Inkling-Small: 39.0 (#53)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1191 |
| Epoch Capabilities Index | 150.13 | 125.27 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |

## Math

- Inkling-Small: 44.9 (#65)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Math | 1453 | 1235 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Inkling-Small: 48.3 (#71)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 88.5% | 40.8% |
| LMArena Expert | 1442 | 1171 |
| SimpleQA Verified | 19.1% | — |
| MMLU | — | 82.4% |

## Multimodal

- Inkling-Small: 38.4 (#59)
- Qwen2-72B: —

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#102)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1400 | 1176 |
| LMArena Chinese | 1458 | 1240 |
| LMArena French | 1438 | 1169 |
| LMArena German | 1412 | 1151 |
| LMArena Japanese | 1399 | 1111 |
| LMArena Korean | 1355 | 1083 |
| LMArena Russian | 1392 | 1169 |
| LMArena Spanish | 1426 | 1168 |

## Instruction Following

- Inkling-Small: 73.9 (#112)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1181 |

## Long Context

- Inkling-Small: 42.7 (#113)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1401 | 1193 |

## Writing & Preference

- Inkling-Small: 59.8 (#102)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Inkling-Small | Qwen2-72B |
|---|---|---|
| LMArena Text | 1413 | 1203 |
| LMArena Creative Writing | 1330 | 1181 |
| LMArena Multi-Turn | 1420 | 1195 |
| EQ-Bench Creative Writing | 1491 | — |

## FAQ

### Is Inkling-Small better than Qwen2-72B?

Inkling-Small is the stronger model overall, scoring 46.5 to 29.5 on the Noometry Index.

### Is Inkling-Small or Qwen2-72B better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 28.7 in the Noometry coding category.

### How many benchmarks do Inkling-Small and Qwen2-72B share?

19 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen2-72B has 26.