# Inkling-Small vs Qwen2.5 7B Instruct

> Inkling-Small is the stronger model overall, scoring 46.5 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 2.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-small-vs-qwen2-5-7b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Inkling-Small scores higher in 6 categories and Qwen2.5 7B Instruct in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 2.5% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 131K.

## Snapshot

| | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 29.0 |
| Rank | 63 | 320 |
| Context | 524K | 131K |
| Input $/M | $0.45 | $0.17 |
| Output $/M | $1.20 | $0.70 |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.6 (#85)
- Qwen2.5 7B Instruct: 36.5 (#208)

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1451 | — |
| BigCodeBench Complete | — | 46.1% |

## Agentic & Tool Use

- Inkling-Small: —
- Qwen2.5 7B Instruct: 23.8 (#124)

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |

## Reasoning

- Inkling-Small: 38.6 (#63)
- Qwen2.5 7B Instruct: 14.8 (#322)

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 18% | 0% |
| Epoch Capabilities Index | 150.15 | 118.51 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| LMArena Hard Prompts | 1423 | — |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |

## Math

- Inkling-Small: 45.1 (#77)
- Qwen2.5 7B Instruct: 12.6 (#306)

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 2.5% |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1459 | — |

## Knowledge

- Inkling-Small: 48.2 (#77)
- Qwen2.5 7B Instruct: 17.0 (#286)

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 88.5% | 35.5% |
| SimpleQA Verified | 19.1% | — |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1442 | — |
| MMLU | — | 72.9% |

## Multimodal

- Inkling-Small: 39.1 (#62)
- Qwen2.5 7B Instruct: —

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#104)
- Qwen2.5 7B Instruct: —

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1402 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1436 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1391 | — |
| LMArena Spanish | 1428 | — |

## Instruction Following

- Inkling-Small: 73.8 (#114)
- Qwen2.5 7B Instruct: 63.2 (#231)

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1399 | — |

## Long Context

- Inkling-Small: 42.7 (#118)
- Qwen2.5 7B Instruct: —

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1401 | — |

## Writing & Preference

- Inkling-Small: 59.6 (#107)
- Qwen2.5 7B Instruct: 48.8 (#195)

| Benchmark | Inkling-Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1414 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1491 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1418 | — |

## FAQ

### Is Inkling-Small better than Qwen2.5 7B Instruct?

Inkling-Small is the stronger model overall, scoring 46.5 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 2.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

### Which is cheaper, Inkling-Small or Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Inkling-Small or Qwen2.5 7B Instruct better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 36.5 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 131K.

### How many benchmarks do Inkling-Small and Qwen2.5 7B Instruct share?

4 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen2.5 7B Instruct has 15.