# Claude 2 vs Phi-4

> Phi-4 is the stronger model overall, scoring 30.9 to 24.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Claude 2 scores higher in 1 category and Phi-4 in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.5 to 17.0.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 64.9% for Phi-4.
- Phi-4 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | Phi-4 |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 24.7 | 30.9 |
| Rank | 342 | 269 |
| Context | — | 128K |
| Input $/M | — | $0.07 |
| Output $/M | — | $0.14 |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- Phi-4: 33.8 (#237)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| LMArena Coding | — | 1231 |
| BigCodeBench Complete | — | 55.4% |
| HumanEval+ | 61.6% | — |

## Agentic & Tool Use

- Claude 2: —
- Phi-4: 22.6 (#120)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Claude 2: 20.8 (#213)
- Phi-4: 17.0 (#287)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| Epoch Capabilities Index | 120.08 | 130.43 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LMArena Hard Prompts | — | 1220 |
| DTBench | 51.9% | — |
| LiveBench Data Analysis | — | 45.2% |
| LiveBench | — | 41.6% |

## Math

- Claude 2: 8.7 (#314)
- Phi-4: 19.6 (#279)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 13.8% |
| MATH Level 5 | 11.7% | 64.9% |
| LiveBench Math | — | 42% |
| LMArena Math | — | 1246 |

## Knowledge

- Claude 2: 17.0 (#282)
- Phi-4: 32.5 (#204)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| GPQA Diamond | 34.7% | 56.1% |
| MMLU | 78.5% | 84.8% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| LMArena Expert | — | 1203 |
| TriviaQA | 87.5% | — |

## Multilingual

- Claude 2: —
- Phi-4: 37.4 (#232)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| LMArena Non-English | — | 1197 |
| LMArena Chinese | — | 1211 |
| LMArena French | — | 1223 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Russian | — | 1209 |
| LMArena Spanish | — | 1234 |

## Instruction Following

- Claude 2: —
- Phi-4: 60.6 (#246)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | — | 58.4% |
| LMArena Instruction Following | — | 1201 |

## Long Context

- Claude 2: —
- Phi-4: 36.9 (#221)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| LMArena Longer Query | — | 1217 |

## Writing & Preference

- Claude 2: —
- Phi-4: 40.7 (#239)

| Benchmark | Claude 2 | Phi-4 |
|---|---|---|
| LMArena Text | — | 1217 |
| LMArena Creative Writing | — | 1182 |
| Short-Story Creative Writing | — | 62.6% |
| LMArena Multi-Turn | — | 1206 |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Claude 2 better than Phi-4?

Phi-4 is the stronger model overall, scoring 30.9 to 24.7 on the Noometry Index.

### How many benchmarks do Claude 2 and Phi-4 share?

5 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Phi-4 has 37.