# Phi-4-reasoning vs Phi-4-reasoning-plus

> Side-by-side benchmark comparison for Phi-4-reasoning and Phi-4-reasoning-plus across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/phi-4-reasoning-vs-phi-4-reasoning-plus
- Last updated: October 14, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Phi-4-reasoning-plus if you want the stronger benchmark profile. Phi-4-reasoning only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Phi-4-reasoning-plus leads overall 50 to 49.
- The biggest single benchmark swing is AIME 2025 in Mathematics, with scores of 62.9% and 78%.

## Model Snapshot

| Property | Phi-4-reasoning | Phi-4-reasoning-plus |
|----------|----------|----------|
| Creator | Microsoft | Microsoft |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 32K | 32K |
| Overall Score | null | null |
| Benchmarks Covered | 6 | 6 |
| Pricing (input/output) | N/A | N/A |

## Category Breakdown

### Coding

- Winner: Not comparable
- Phi-4-reasoning public-lane score: Coming soon
- Phi-4-reasoning-plus public-lane score: Coming soon

| Benchmark | Phi-4-reasoning | Phi-4-reasoning-plus | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench | 53.8% | 53.1% | Phi-4-reasoning |

### Knowledge

- Winner: Not comparable
- Phi-4-reasoning public-lane score: Coming soon
- Phi-4-reasoning-plus public-lane score: Coming soon

| Benchmark | Phi-4-reasoning | Phi-4-reasoning-plus | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 65.8% | 68.9% | Phi-4-reasoning-plus |
| MMLU-Pro | 74.3% | 76% | Phi-4-reasoning-plus |

### Instruction Following

- Winner: Not comparable
- Phi-4-reasoning public-lane score: Coming soon
- Phi-4-reasoning-plus public-lane score: Coming soon

| Benchmark | Phi-4-reasoning | Phi-4-reasoning-plus | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 83.4% | 84.9% | Phi-4-reasoning-plus |

### Mathematics

- Winner: Not comparable
- Phi-4-reasoning public-lane score: Coming soon
- Phi-4-reasoning-plus public-lane score: Coming soon

| Benchmark | Phi-4-reasoning | Phi-4-reasoning-plus | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | 75.3% | 81.3% | Phi-4-reasoning-plus |
| AIME 2025 | 62.9% | 78% | Phi-4-reasoning-plus |

## FAQ

### Which is better overall, Phi-4-reasoning or Phi-4-reasoning-plus?

Phi-4-reasoning-plus is ahead overall on BenchLM right now.

### How many benchmarks does Phi-4-reasoning cover on BenchLM?

Phi-4-reasoning currently has 6 sourced benchmark scores on BenchLM.

### How many benchmarks does Phi-4-reasoning-plus cover on BenchLM?

Phi-4-reasoning-plus currently has 6 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Phi-4-reasoning vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-phi-4-reasoning)
- [Phi-4-reasoning-plus vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-phi-4-reasoning-plus)
- [Phi-4-reasoning vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-phi-4-reasoning)
- [Phi-4-reasoning-plus vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-phi-4-reasoning-plus)

## Explore More

- [Phi-4-reasoning profile](/models/phi-4-reasoning)
- [Phi-4-reasoning-plus profile](/models/phi-4-reasoning-plus)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)