# Phi-4-reasoning-plus vs Qwen3 235B-A22B (Reasoning)

> Side-by-side benchmark comparison for Phi-4-reasoning-plus and Qwen3 235B-A22B (Reasoning) across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/phi-4-reasoning-plus-vs-qwen3-235b-a22b-reasoning
- Last updated: October 14, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Qwen3 235B-A22B (Reasoning) if you want the stronger benchmark profile. Phi-4-reasoning-plus only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Qwen3 235B-A22B (Reasoning) leads overall 64 to 50.
- The biggest single benchmark swing is AIME 2024 in Mathematics, with scores of 81.3% and 85.7%.
- Qwen3 235B-A22B (Reasoning) also has the larger context window at 128K.

## Model Snapshot

| Property | Phi-4-reasoning-plus | Qwen3 235B-A22B (Reasoning) |
|----------|----------|----------|
| Creator | Microsoft | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 32K | 128K |
| Overall Score | null | null |
| Benchmarks Covered | 6 | 11 |
| Pricing (input/output) | N/A | N/A |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Phi-4-reasoning-plus public-lane score: Coming soon
- Qwen3 235B-A22B (Reasoning) public-lane score: Coming soon

| Benchmark | Phi-4-reasoning-plus | Qwen3 235B-A22B (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| BFCL v3 | Coming soon | 70.8% | Coming soon |

### Coding

- Winner: Not comparable
- Phi-4-reasoning-plus public-lane score: Coming soon
- Qwen3 235B-A22B (Reasoning) public-lane score: Coming soon

| Benchmark | Phi-4-reasoning-plus | Qwen3 235B-A22B (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench | 53.1% | Coming soon | Coming soon |
| LiveCodeBench v5 | Coming soon | 70.7% | Coming soon |

### Knowledge

- Winner: Not comparable
- Phi-4-reasoning-plus public-lane score: Coming soon
- Qwen3 235B-A22B (Reasoning) public-lane score: Coming soon

| Benchmark | Phi-4-reasoning-plus | Qwen3 235B-A22B (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 68.9% | 71.1% | Qwen3 235B-A22B (Reasoning) |
| MMLU-Pro | 76% | Coming soon | Coming soon |
| MMLU-Redux | Coming soon | 92.7% | Coming soon |
| C-Eval | Coming soon | 89.6% | Coming soon |
| MMMLU | Coming soon | 84.3% | Coming soon |

### Multilingual

- Winner: Not comparable
- Phi-4-reasoning-plus public-lane score: Coming soon
- Qwen3 235B-A22B (Reasoning) public-lane score: Coming soon

| Benchmark | Phi-4-reasoning-plus | Qwen3 235B-A22B (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| INCLUDE | Coming soon | 78.7% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Phi-4-reasoning-plus public-lane score: Coming soon
- Qwen3 235B-A22B (Reasoning) public-lane score: Coming soon

| Benchmark | Phi-4-reasoning-plus | Qwen3 235B-A22B (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 84.9% | 83.4% | Phi-4-reasoning-plus |

### Mathematics

- Winner: Not comparable
- Phi-4-reasoning-plus public-lane score: Coming soon
- Qwen3 235B-A22B (Reasoning) public-lane score: Coming soon

| Benchmark | Phi-4-reasoning-plus | Qwen3 235B-A22B (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | 81.3% | 85.7% | Qwen3 235B-A22B (Reasoning) |
| AIME 2025 | 78% | 81.5% | Qwen3 235B-A22B (Reasoning) |
| MATH-500 | Coming soon | 98% | Coming soon |

## FAQ

### Which is better overall, Phi-4-reasoning-plus or Qwen3 235B-A22B (Reasoning)?

Qwen3 235B-A22B (Reasoning) is ahead overall on BenchLM right now.

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

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

### How many benchmarks does Qwen3 235B-A22B (Reasoning) cover on BenchLM?

Qwen3 235B-A22B (Reasoning) currently has 11 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Phi-4-reasoning-plus vs Phi-4-reasoning](/compare/phi-4-reasoning-vs-phi-4-reasoning-plus)
- [Qwen3 235B-A22B (Reasoning) vs Phi-4-reasoning](/compare/phi-4-reasoning-vs-qwen3-235b-a22b-reasoning)
- [Phi-4-reasoning-plus vs Qwen3 235B-A22B](/compare/phi-4-reasoning-plus-vs-qwen3-235b-a22b)
- [Qwen3 235B-A22B (Reasoning) vs Qwen3 235B-A22B](/compare/qwen3-235b-a22b-vs-qwen3-235b-a22b-reasoning)

## Explore More

- [Phi-4-reasoning-plus profile](/models/phi-4-reasoning-plus)
- [Qwen3 235B-A22B (Reasoning) profile](/models/qwen3-235b-a22b-reasoning)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)