# Inkling vs Phi 3 Small 8k Instruct

> Inkling is the stronger model overall, scoring 44.1 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Inkling scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.2 to 31.1.

## Snapshot

| | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Thinking Machines Lab | Microsoft |
| Noometry Index | 44.1 | 29.3 |
| Rank | 80 | 314 |
| Context | 66K | — |
| Input $/M | $1.87 | — |
| Output $/M | $4.68 | — |
| Weights | Open | Open |

## Coding

- Inkling: 34.5 (#234)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1464 | 1101 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 946 | — |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- Phi 3 Small 8k Instruct: —

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.4 (#56)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1100 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 87.5% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 37.6% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 148.54 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- Inkling: 31.3 (#225)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1479 | 1151 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| LiveBench Math | — | 17.6% |

## Knowledge

- Inkling: 55.1 (#49)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1465 | 1067 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- Inkling: 54.0 (#52)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1434 | 1058 |
| LMArena Chinese | 1490 | 1061 |
| LMArena French | 1458 | 1135 |
| LMArena German | 1446 | 1080 |
| LMArena Japanese | 1429 | 966 |
| LMArena Korean | 1404 | 894 |
| LMArena Russian | 1429 | 1111 |
| LMArena Spanish | 1448 | 1111 |

## Instruction Following

- Inkling: 75.1 (#71)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1426 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- Inkling: 43.8 (#86)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1434 | 1088 |

## Writing & Preference

- Inkling: 65.2 (#51)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | Inkling | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1441 | 1110 |
| LMArena Creative Writing | 1387 | 1083 |
| LMArena Multi-Turn | 1436 | 1068 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LiveBench Language | — | 12.9% |

## FAQ

### Is Inkling better than Phi 3 Small 8k Instruct?

Inkling is the stronger model overall, scoring 44.1 to 29.3 on the Noometry Index.

### Is Inkling or Phi 3 Small 8k Instruct better for coding?

Inkling scores higher on coding benchmarks: 34.5 versus 27.9 in the Noometry coding category.

### How many benchmarks do Inkling and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Phi 3 Small 8k Instruct has 32.