# LongCat-2.5 vs Ornith-1.5-35B-A3B

> Side-by-side benchmark comparison for LongCat-2.5 and Ornith-1.5-35B-A3B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/longcat-2-5-vs-ornith-1-5-35b-a3b
- Last updated: November 9, 2026

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

## Quick Verdict

Ornith-1.5-35B-A3B leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Ornith-1.5-35B-A3B has the higher overall point estimate 35.98 to 0. Conditional score ranges do not establish rank confidence.
- The biggest single benchmark swing is DeepSWE in Coding, with scores of 64.6% and 22.0%.
- Ornith-1.5-35B-A3B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- LongCat-2.5 also has the larger context window at 1M.

## Model Snapshot

| Property | LongCat-2.5 | Ornith-1.5-35B-A3B |
|----------|----------|----------|
| Creator | Meituan | Ornith AI |
| Type | Open Weight | Open Weight |
| Reasoning | Hybrid | Reasoning |
| Context | 1M | 262K |
| Overall Score | null | 35.98 |
| Benchmarks Covered | 22 | 18 |
| Pricing (input/output) | $0.30 / $1.20 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- LongCat-2.5 public-lane score: Coming soon
- Ornith-1.5-35B-A3B public-lane score: 32.2 (Estimated · #99/132)

| Benchmark | LongCat-2.5 | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 88.4% | 67.8% | LongCat-2.5 |
| Terminal-Bench 4.0 | 38.50% | Coming soon | Coming soon |
| BrowseComp | 91.9% | 67.6% | LongCat-2.5 |
| AutomationBench | 51.8% | Coming soon | Coming soon |
| HLE w/ tools | 63.1% | 33.4% | LongCat-2.5 |
| Agents' Last Exam | 38.5% | Coming soon | Coming soon |
| MCP Atlas | 83.1% | 70.2% | LongCat-2.5 |
| JobBench | 65.4% | Coming soon | Coming soon |
| skillsBench | 63.3% | Coming soon | Coming soon |
| SpreadsheetBench 2 | 34.9% | Coming soon | Coming soon |
| Claw-Eval | 78.3% | 72.5% | LongCat-2.5 |
| Toolathlon-Verified | Coming soon | 48.7% | Coming soon |
| WideResearch | Coming soon | 67.8% | Coming soon |

### Coding

- Winner: Not comparable
- LongCat-2.5 public-lane score: Coming soon
- Ornith-1.5-35B-A3B public-lane score: 28.4 (Estimated · #116/158)

| Benchmark | LongCat-2.5 | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 88.4% | 67.8% | LongCat-2.5 |
| ProgramBench | 25.5% | Coming soon | Coming soon |
| DeepSWE | 64.6% | 22.0% | LongCat-2.5 |
| PaperBench | 82.1% | Coming soon | Coming soon |
| SWE-Atlas Codebase QnA | 58.3% | Coming soon | Coming soon |
| NL2Repo | 60.5% | 46.2% | LongCat-2.5 |
| SWE-bench Verified | Coming soon | 79% | Coming soon |
| SWE-bench Pro | Coming soon | 59.6% | Coming soon |
| SWE Multilingual | Coming soon | 71.4% | Coming soon |
| frontierBench | Coming soon | 5.1% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- LongCat-2.5 public-lane score: Coming soon
- Ornith-1.5-35B-A3B public-lane score: Coming soon

| Benchmark | LongCat-2.5 | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Vision2Web | 78.6% | Coming soon | Coming soon |
| CharXiv | 90.2% | Coming soon | Coming soon |
| MathVision w/ Python | 96.5% | Coming soon | Coming soon |
| Video-MME | 85.2% | Coming soon | Coming soon |

### Knowledge

- Winner: Not comparable
- LongCat-2.5 public-lane score: Coming soon
- Ornith-1.5-35B-A3B public-lane score: 39.6 (Estimated · #118/179)

| Benchmark | LongCat-2.5 | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| FrontierScience | 77% | Coming soon | Coming soon |
| GPQA | Coming soon | 89.2% | Coming soon |
| GPQA-D | Coming soon | 89.2% | Coming soon |
| HLE | Coming soon | 25.6% | Coming soon |
| HLE w/o tools | Coming soon | 25.6% | Coming soon |

## FAQ

### Which is better overall, LongCat-2.5 or Ornith-1.5-35B-A3B?

Ornith-1.5-35B-A3B has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### How many benchmarks does LongCat-2.5 cover on BenchLM?

LongCat-2.5 currently has 22 sourced benchmark scores on BenchLM.

### How many benchmarks does Ornith-1.5-35B-A3B cover on BenchLM?

Ornith-1.5-35B-A3B currently has 18 sourced benchmark scores on BenchLM.

## Related Comparisons

- [LongCat-2.5 vs Ornith-1.5-397B](/compare/longcat-2-5-vs-ornith-1-5-397b)
- [Ornith-1.5-35B-A3B vs Ornith-1.5-397B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-397b)
- [LongCat-2.5 vs Ornith-1.5-9B](/compare/longcat-2-5-vs-ornith-1-5-9b)
- [Ornith-1.5-35B-A3B vs Ornith-1.5-9B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-9b)

## Explore More

- [LongCat-2.5 profile](/models/longcat-2-5)
- [Ornith-1.5-35B-A3B profile](/models/ornith-1-5-35b-a3b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)