# Ornith-1.5-397B vs SWE-2

> Side-by-side benchmark comparison for Ornith-1.5-397B and SWE-2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/ornith-1-5-397b-vs-swe-2
- Last updated: September 10, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Ornith-1.5-397B and SWE-2 share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- SWE-2 has the lower published output-token price.
- SWE-2 has the larger published context window at 1M.

## Model Snapshot

| Property | Ornith-1.5-397B | SWE-2 |
|----------|----------|----------|
| Creator | Ornith AI | Cognition |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 1M |
| Independent public score (not head-to-head) | 65.4 | null |
| Benchmarks Covered | 18 | 5 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Ornith-1.5-397B public-lane score: 60.8 (Estimated · #18/152)
- SWE-2 public-lane score: Coming soon

| Benchmark | Ornith-1.5-397B | SWE-2 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 86.1% | 92.8% | SWE-2 |
| HLE w/ tools | 56.1% | Coming soon | Coming soon |
| MCP Atlas | 80% | Coming soon | Coming soon |
| Toolathlon-Verified | 71.2% | Coming soon | Coming soon |
| WideResearch | 80.8% | Coming soon | Coming soon |
| BrowseComp | 86.6% | Coming soon | Coming soon |
| Claw-Eval | 81.4% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 27.30% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Ornith-1.5-397B public-lane score: 58.8 (Estimated · #26/151)
- SWE-2 public-lane score: Coming soon

| Benchmark | Ornith-1.5-397B | SWE-2 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 86.1% | 92.8% | SWE-2 |
| SWE-bench Verified | 86% | Coming soon | Coming soon |
| SWE-bench Pro | 65.1% | Coming soon | Coming soon |
| SWE Multilingual | 79.6% | Coming soon | Coming soon |
| DeepSWE | 56.0% | 73.0% | SWE-2 |
| frontierBench | 13.5% | Coming soon | Coming soon |
| NL2Repo | 59.5% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | Coming soon | 50.0% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Ornith-1.5-397B public-lane score: 60.4 (Estimated · #36/183)
- SWE-2 public-lane score: Coming soon

| Benchmark | Ornith-1.5-397B | SWE-2 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 92.8% | Coming soon | Coming soon |
| GPQA-D | 92.8% | Coming soon | Coming soon |
| HLE | 44.6% | Coming soon | Coming soon |
| HLE w/o tools | 44.6% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between Ornith-1.5-397B and SWE-2?

Not yet. The models share only 3 sourced benchmark rows, 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-1.5-397B vs Ornith-1.5-35B-A3B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-397b)
- [SWE-2 vs Ornith-1.5-35B-A3B](/compare/ornith-1-5-35b-a3b-vs-swe-2)
- [Ornith-1.5-397B vs Ornith-1.5-9B](/compare/ornith-1-5-397b-vs-ornith-1-5-9b)
- [SWE-2 vs Ornith-1.5-9B](/compare/ornith-1-5-9b-vs-swe-2)

## Explore More

- [Ornith-1.5-397B profile](/models/ornith-1-5-397b)
- [SWE-2 profile](/models/swe-2)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)