# Claude Opus 5 vs Phi-3.5-mini

> Claude Opus 5 has enough public results to be ranked (#4); Phi-3.5-mini does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/claude-opus-5-vs-phi-3-5-mini
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Claude Opus 5 leads 67.5 to 34.6.
- Phi-3.5-mini has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 67.8 | 36.9 |
| Rank | 4 | — |
| Context | 1M | — |
| Input $/M | $5 | — |
| Output $/M | $25 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 5: 67.5 (#5)
- Phi-3.5-mini: 34.6 (#232)

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
| SciCode | 56.4% | — |
| WeirdML | 91.8% | — |
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1534 | — |
| BigCodeBench Complete | — | 38.5% |
| ALE-Bench | 2,165 | — |

## Agentic & Tool Use

- Claude Opus 5: 55.6 (#1)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| APEX-Agents | 65.8% | — |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |

## Reasoning

- Claude Opus 5: 77.2 (#4)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| NYT Connections (extended) | 94.3% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 29.1% | — |
| Chess Puzzles | 42% | — |
| EBR-Bench | 45.7% | — |
| LMArena Hard Prompts | 1526 | — |
| Mystery Game Puzzles | 59% | — |
| DTBench | 97.9% | — |
| LMCA | 64.5% | — |
| Bench to the Future 3 | 0.12 | — |
| Epoch Capabilities Index | 162.78 | — |
| PIQA | — | 81% |

## Math

- Claude Opus 5: 86.2 (#8)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 99% | — |
| LMArena Math | 1531 | — |
| GSM8K | — | 86.2% |

## Knowledge

- Claude Opus 5: 66.8 (#9)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 93.9% | — |
| SimpleQA Verified | 59.9% | — |
| LMArena Expert | 1557 | — |
| BoolQ | — | 78% |

## Multimodal

- Claude Opus 5: 50.8 (#8)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |

## Multilingual

- Claude Opus 5: 58.8 (#4)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1501 | — |
| LMArena Chinese | 1574 | — |
| LMArena French | 1519 | — |
| LMArena German | 1524 | — |
| LMArena Japanese | 1516 | — |
| LMArena Korean | 1521 | — |
| LMArena Russian | 1507 | — |
| LMArena Spanish | 1519 | — |

## Instruction Following

- Claude Opus 5: 79.2 (#7)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1517 | — |

## Long Context

- Claude Opus 5: 46.5 (#21)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1515 | — |

## Writing & Preference

- Claude Opus 5: 79.2 (#1)
- Phi-3.5-mini: —

| Benchmark | Claude Opus 5 | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1507 | — |
| LMArena Creative Writing | 1491 | — |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |
| LMArena Multi-Turn | 1499 | — |

## FAQ

### Is Claude Opus 5 better than Phi-3.5-mini?

Claude Opus 5 has enough public results to be ranked (#4); Phi-3.5-mini does not yet, so treat this comparison as directional.

### Is Claude Opus 5 or Phi-3.5-mini better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 34.6 in the Noometry coding category.

### How many benchmarks do Claude Opus 5 and Phi-3.5-mini share?

0 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Phi-3.5-mini has 5.