# Ornith-1.0-35B vs Ornith-1.5-35B-A3B

> Side-by-side benchmark comparison for Ornith-1.0-35B and Ornith-1.5-35B-A3B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/ornith-1-0-35b-vs-ornith-1-5-35b-a3b
- Last updated: October 2, 2026

- Shared sourced benchmarks: 7
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Ornith-1.0-35B leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Ornith-1.0-35B has the higher overall point estimate 45 to 32.61. Conditional score ranges do not establish rank confidence.
- The biggest single benchmark swing is NL2Repo in Coding, with scores of 34.6% and 46.2%.
- Ornith-1.5-35B-A3B also has the larger context window at 262K.

## Model Snapshot

| Property | Ornith-1.0-35B | Ornith-1.5-35B-A3B |
|----------|----------|----------|
| Creator | DeepReinforce AI | Ornith AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 262K |
| Overall Score | null | 32.61 |
| Benchmarks Covered | 7 | 18 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Ornith-1.0-35B public-lane score: Coming soon
- Ornith-1.5-35B-A3B public-lane score: 23.5 (Estimated · #95/119)

| Benchmark | Ornith-1.0-35B | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 64.2% | 67.8% | Ornith-1.5-35B-A3B |
| Claw-Eval | 69.8% | 72.5% | Ornith-1.5-35B-A3B |
| HLE w/ tools | Coming soon | 33.4% | Coming soon |
| MCP Atlas | Coming soon | 70.2% | Coming soon |
| Toolathlon-Verified | Coming soon | 48.7% | Coming soon |
| WideResearch | Coming soon | 67.8% | Coming soon |
| BrowseComp | Coming soon | 67.6% | Coming soon |

### Coding

- Winner: Not comparable
- Ornith-1.0-35B public-lane score: Coming soon
- Ornith-1.5-35B-A3B public-lane score: 24 (Estimated · #110/144)

| Benchmark | Ornith-1.0-35B | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 75.6% | 79% | Ornith-1.5-35B-A3B |
| SWE-bench Pro | 50.4% | 59.6% | Ornith-1.5-35B-A3B |
| SWE Multilingual | 69.3% | 71.4% | Ornith-1.5-35B-A3B |
| NL2Repo | 34.6% | 46.2% | Ornith-1.5-35B-A3B |
| Terminal-Bench 2.1 | 64.2% | 67.8% | Ornith-1.5-35B-A3B |
| DeepSWE | Coming soon | 22.0% | Coming soon |
| frontierBench | Coming soon | 5.1% | Coming soon |

### Knowledge

- Winner: Not comparable
- Ornith-1.0-35B public-lane score: Coming soon
- Ornith-1.5-35B-A3B public-lane score: 34.5 (Estimated · #119/171)

| Benchmark | Ornith-1.0-35B | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| 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, Ornith-1.0-35B or Ornith-1.5-35B-A3B?

Ornith-1.0-35B has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### How many benchmarks does Ornith-1.0-35B cover on BenchLM?

Ornith-1.0-35B currently has 7 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

- [Ornith-1.0-35B vs Ornith-1.0-397B](/compare/ornith-1-0-35b-vs-ornith-1-0-397b)
- [Ornith-1.5-35B-A3B vs Ornith-1.0-397B](/compare/ornith-1-0-397b-vs-ornith-1-5-35b-a3b)
- [Ornith-1.0-35B vs Ornith-1.0-9B](/compare/ornith-1-0-35b-vs-ornith-1-0-9b)
- [Ornith-1.5-35B-A3B vs Ornith-1.0-9B](/compare/ornith-1-0-9b-vs-ornith-1-5-35b-a3b)

## Explore More

- [Ornith-1.0-35B profile](/models/ornith-1-0-35b)
- [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)