# GPT-6 Astra vs Phi 3 Small 8k Instruct

> GPT-6 Astra is the stronger model overall, scoring 70.3 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-6-astra-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. GPT-6 Astra 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 reasoning, where GPT-6 Astra leads 85.1 to 14.2.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 70.3 | 28.8 |
| Rank | 1 | 310 |
| Context | 1.05M | — |
| Input $/M | $10 | — |
| Output $/M | $50 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-6 Astra: 70.5 (#3)
- Phi 3 Small 8k Instruct: 27.4 (#313)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1488 | 1102 |
| DeepSWE | 74.1% | — |
| FrontierCode | 53.3% | — |
| LMArena WebDev | 1792 | — |
| FrontierSWE | 65.5% | — |
| SciCode | 56.5% | — |
| WeirdML | 93.6% | — |
| LiveBench Coding | — | 20.3% |
| MirrorCode | 46.7% | — |
| ALE-Bench | 2,951 | — |

## Agentic & Tool Use

- GPT-6 Astra: 52.3 (#3)
- Phi 3 Small 8k Instruct: —

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| APEX-Agents | 64.7% | — |
| Remote Labor Index | 20.8% | — |
| BALROG | 68.3% | — |
| Vending-Bench 2 | 15,515 | — |

## Reasoning

- GPT-6 Astra: 85.1 (#1)
- Phi 3 Small 8k Instruct: 14.2 (#319)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1464 | 1100 |
| ARC-AGI-2 | 95% | — |
| NYT Connections (extended) | 98.1% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 31.7% | — |
| Chess Puzzles | 72% | — |
| EBR-Bench | 76.2% | — |
| LiveBench Reasoning | — | 15.9% |
| Mystery Game Puzzles | 84% | — |
| DTBench | 97.3% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 64.4% | — |
| Adversarial NLI | — | 58.1% |
| Bench to the Future 3 | 0.14 | — |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 166.6 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- GPT-6 Astra: 93.4 (#1)
- Phi 3 Small 8k Instruct: 25.4 (#247)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1463 | 1151 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 97.6% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 99% | — |
| LiveBench Math | — | 17.6% |
| FrontierMath Erdős | 2.9% | — |

## Knowledge

- GPT-6 Astra: 75.3 (#1)
- Phi 3 Small 8k Instruct: 28.5 (#237)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1486 | 1067 |
| GPQA Diamond | 95.8% | — |
| Humanity's Last Exam | 54.8% | — |
| SimpleQA Verified | 75.6% | — |
| Vectara Hallucination Rate | 8.7% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multimodal

- GPT-6 Astra: 55.1 (#3)
- Phi 3 Small 8k Instruct: —

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1280 | — |
| Blueprint-Bench 2 | 49.7% | — |
| Furniture Assembly | 80% | — |
| LMArena Document | 1468 | — |

## Multilingual

- GPT-6 Astra: 54.0 (#53)
- Phi 3 Small 8k Instruct: 28.6 (#267)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1431 | 1058 |
| LMArena Chinese | 1495 | 1061 |
| LMArena French | 1467 | 1134 |
| LMArena Russian | 1434 | 1111 |
| LMArena Spanish | 1412 | 1111 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |

## Instruction Following

- GPT-6 Astra: 76.6 (#37)
- Phi 3 Small 8k Instruct: 52.2 (#287)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1454 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- GPT-6 Astra: 44.7 (#57)
- Phi 3 Small 8k Instruct: 33.0 (#262)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1460 | 1088 |

## Writing & Preference

- GPT-6 Astra: 75.7 (#7)
- Phi 3 Small 8k Instruct: 31.3 (#279)

| Benchmark | GPT-6 Astra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1443 | 1110 |
| LMArena Creative Writing | 1423 | 1083 |
| LMArena Multi-Turn | 1457 | 1068 |
| EQ-Bench Creative Writing | 2173 | — |
| LiveBench Language | — | 12.9% |

## FAQ

### Is GPT-6 Astra better than Phi 3 Small 8k Instruct?

GPT-6 Astra is the stronger model overall, scoring 70.3 to 28.8 on the Noometry Index.

### Is GPT-6 Astra or Phi 3 Small 8k Instruct better for coding?

GPT-6 Astra scores higher on coding benchmarks: 70.5 versus 27.4 in the Noometry coding category.

### How many benchmarks do GPT-6 Astra and Phi 3 Small 8k Instruct share?

14 benchmarks have published results for both models. GPT-6 Astra has 51 scored results on Noometry and Phi 3 Small 8k Instruct has 32.