# Claude Opus 4.6 vs Phi-4

> Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 31.2 on the Noometry Index. Phi-4 costs 114× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-6-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.6 leads 63.0 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for Claude Opus 4.6 and 13.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
- Claude Opus 4.6 accepts more context: 1M tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 58.2 | 31.2 |
| Rank | 20 | 279 |
| Context | 1M | 128K |
| Input $/M | $5 | $0.07 |
| Output $/M | $25 | $0.14 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 4.6: 57.2 (#20)
- Phi-4: 34.4 (#239)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| LMArena Coding | 1536 | 1231 |
| SWE-bench Verified | 78.7% | — |
| FrontierCode | 26.6% | — |
| SWE-bench Verified (bash only) | 75.6% | — |
| LMArena WebDev | 1547 | — |
| SWE-bench Multilingual | 72% | — |
| GSO | 41.2% | — |
| WeirdML | 78% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| ALE-Bench | 996.5 | — |
| AlgoTune | 1.47 | — |

## Agentic & Tool Use

- Claude Opus 4.6: 51.1 (#4)
- Phi-4: 22.8 (#128)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| Terminal-Bench | 79.8% | — |
| APEX-Agents | 46.3% | — |
| Berkeley Function Calling Leaderboard | — | 28.8% |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| BALROG | — | 11.6% |
| GBAEval | 44.1% | — |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |
| Vending-Bench 2 | 8,018 | — |

## Reasoning

- Claude Opus 4.6: 57.8 (#23)
- Phi-4: 17.7 (#291)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| Chess Puzzles | 17% | 1% |
| LMArena Hard Prompts | 1527 | 1220 |
| Epoch Capabilities Index | 155.24 | 130.42 |
| ARC-AGI-2 | 69.2% | — |
| SimpleBench | 67.6% | — |
| Kagi LLM Benchmark | 83.6% | — |
| NYT Connections (extended) | 92.1% | — |
| ARC-AGI-1 | 94% | — |
| EnigmaEval | 7.6% | — |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |
| LiveBench Reasoning | — | 47.8% |
| Mystery Game Puzzles | 25% | — |
| DTBench | 91.2% | — |
| LiveBench Data Analysis | — | 45.2% |
| LMCA | 55.8% | — |
| ForecastBench | 60 | — |
| LiveBench | — | 41.6% |

## Math

- Claude Opus 4.6: 63.0 (#31)
- Phi-4: 20.8 (#285)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 13.8% |
| LMArena Math | 1519 | 1246 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 78.5% | — |
| ProofBench | 50% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |

## Knowledge

- Claude Opus 4.6: 61.9 (#26)
- Phi-4: 32.6 (#209)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| GPQA Diamond | 90.5% | 56.1% |
| Vectara Hallucination Rate | 12.2% | 3.7% |
| LMArena Expert | 1546 | 1203 |
| Humanity's Last Exam | 34.4% | — |
| SimpleQA Verified | 47% | — |
| Confabulations | — | 29.4% |
| MMLU | — | 84.8% |

## Multimodal

- Claude Opus 4.6: 37.3 (#74)
- Phi-4: —

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| LMArena Vision | 1316 | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |

## Multilingual

- Claude Opus 4.6: 57.9 (#6)
- Phi-4: 37.2 (#237)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| LMArena Non-English | 1489 | 1197 |
| LMArena Chinese | 1551 | 1212 |
| LMArena French | 1513 | 1224 |
| LMArena German | 1502 | 1222 |
| LMArena Japanese | 1484 | 1158 |
| LMArena Korean | 1464 | 1151 |
| LMArena Russian | 1497 | 1209 |
| LMArena Spanish | 1510 | 1234 |

## Instruction Following

- Claude Opus 4.6: 79.5 (#4)
- Phi-4: 60.4 (#251)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1523 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- Claude Opus 4.6: 48.1 (#13)
- Phi-4: 36.9 (#226)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1520 | 1217 |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |

## Writing & Preference

- Claude Opus 4.6: 73.5 (#10)
- Phi-4: 40.5 (#244)

| Benchmark | Claude Opus 4.6 | Phi-4 |
|---|---|---|
| LMArena Text | 1503 | 1217 |
| LMArena Creative Writing | 1505 | 1182 |
| LMArena Multi-Turn | 1513 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 1809 | — |
| EQ-Bench 4 | 1223 | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Claude Opus 4.6 better than Phi-4?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 31.2 on the Noometry Index. Phi-4 costs 114× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.6 or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

### Is Claude Opus 4.6 or Phi-4 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 128K.

### How many benchmarks do Claude Opus 4.6 and Phi-4 share?

22 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Phi-4 has 37.