# Ornith-1.5-35B-A3B vs Phi-4-reasoning

> Side-by-side benchmark comparison for Ornith-1.5-35B-A3B and Phi-4-reasoning across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/ornith-1-5-35b-a3b-vs-phi-4-reasoning
- Last updated: October 14, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Ornith-1.5-35B-A3B and Phi-4-reasoning share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Ornith-1.5-35B-A3B has the larger published context window at 262K.

## Model Snapshot

| Property | Ornith-1.5-35B-A3B | Phi-4-reasoning |
|----------|----------|----------|
| Creator | Ornith AI | Microsoft |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 32K |
| Independent public score (not head-to-head) | 35.65 | null |
| Benchmarks Covered | 18 | 6 |
| Pricing (input/output) | $0.00 / $0.00 | N/A |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Ornith-1.5-35B-A3B public-lane score: 27.9 (Estimated · #93/124)
- Phi-4-reasoning public-lane score: Coming soon

| Benchmark | Ornith-1.5-35B-A3B | Phi-4-reasoning | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 67.8% | Coming soon | Coming soon |
| HLE w/ tools | 33.4% | Coming soon | Coming soon |
| MCP Atlas | 70.2% | Coming soon | Coming soon |
| Toolathlon-Verified | 48.7% | Coming soon | Coming soon |
| WideResearch | 67.8% | Coming soon | Coming soon |
| BrowseComp | 67.6% | Coming soon | Coming soon |
| Claw-Eval | 72.5% | Coming soon | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Ornith-1.5-35B-A3B public-lane score: 25.8 (Estimated · #104/149)
- Phi-4-reasoning public-lane score: Coming soon

| Benchmark | Ornith-1.5-35B-A3B | Phi-4-reasoning | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 67.8% | Coming soon | Coming soon |
| SWE-bench Verified | 79% | Coming soon | Coming soon |
| SWE-bench Pro | 59.6% | Coming soon | Coming soon |
| SWE Multilingual | 71.4% | Coming soon | Coming soon |
| DeepSWE | 22.0% | Coming soon | Coming soon |
| frontierBench | 5.1% | Coming soon | Coming soon |
| NL2Repo | 46.2% | Coming soon | Coming soon |
| LiveCodeBench | Coming soon | 53.8% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Ornith-1.5-35B-A3B public-lane score: 39.5 (Estimated · #118/181)
- Phi-4-reasoning public-lane score: Coming soon

| Benchmark | Ornith-1.5-35B-A3B | Phi-4-reasoning | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 89.2% | 65.8% | Ornith-1.5-35B-A3B |
| GPQA-D | 89.2% | Coming soon | Coming soon |
| HLE | 25.6% | Coming soon | Coming soon |
| HLE w/o tools | 25.6% | Coming soon | Coming soon |
| MMLU-Pro | Coming soon | 74.3% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Ornith-1.5-35B-A3B public-lane score: Coming soon
- Phi-4-reasoning public-lane score: Coming soon

| Benchmark | Ornith-1.5-35B-A3B | Phi-4-reasoning | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 83.4% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Ornith-1.5-35B-A3B public-lane score: Coming soon
- Phi-4-reasoning public-lane score: Coming soon

| Benchmark | Ornith-1.5-35B-A3B | Phi-4-reasoning | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | Coming soon | 75.3% | Coming soon |
| AIME 2025 | Coming soon | 62.9% | Coming soon |

## FAQ

### Is there enough evidence to pick between Ornith-1.5-35B-A3B and Phi-4-reasoning?

Not yet. The models share only 1 sourced benchmark row, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Ornith-1.5-35B-A3B vs Ornith-1.5-397B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-397b)
- [Phi-4-reasoning vs Ornith-1.5-397B](/compare/ornith-1-5-397b-vs-phi-4-reasoning)
- [Ornith-1.5-35B-A3B vs Ornith-1.5-9B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-9b)
- [Phi-4-reasoning vs Ornith-1.5-9B](/compare/ornith-1-5-9b-vs-phi-4-reasoning)

## Explore More

- [Ornith-1.5-35B-A3B profile](/models/ornith-1-5-35b-a3b)
- [Phi-4-reasoning profile](/models/phi-4-reasoning)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)