# Ornith-1.5-35B-A3B Benchmark Scores & Performance

> Ornith-1.5-35B-A3B by Ornith AI scores 32.61/100 overall, ranking #156 out of 783 AI models.

Canonical page: https://benchlm.ai/models/ornith-1-5-35b-a3b

Last updated: October 2, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Ornith AI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 262K |
| Official model card | [Ornith-1.5-35B-A3B model card](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B) |
| Overall Score | 32.61/100 |
| Overall Rank | #156 of 783 |

## Family & Coverage

- Family: Ornith 1.5
- Variant: 35b-a3b (35B-A3B)
- Benchmarks covered: 18 of 645
- Sibling models: [Ornith-1.5-397B](/models/ornith-1-5-397b), [Ornith-1.5-9B](/models/ornith-1-5-9b)
- Related earlier model: [Ornith-1.0-35B](/models/ornith-1-0-35b)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 67.8% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [HLE w/ tools](/benchmarks/hlewithtools) | 33.4% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [MCP Atlas](/benchmarks/mcpatlas) | 70.2% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [Toolathlon-Verified](/benchmarks/toolathlonverified) | 48.7% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [WideResearch](/benchmarks/wideresearch) | 67.8% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [BrowseComp](/benchmarks/browsecomp) | 67.6% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [Claw-Eval](/benchmarks/claw-eval) | 72.5% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 67.8% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 79% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 59.6% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 71.4% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [DeepSWE](/benchmarks/deepswe) | 22.0% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [frontierBench](/benchmarks/terminal-bench-3) | 5.1% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [NL2Repo](/benchmarks/nl2repo) | 46.2% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA](/benchmarks/gpqa) | 89.2% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [GPQA-D](/benchmarks/gpqa-diamond) | 89.2% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [HLE](/benchmarks/hle) | 25.6% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |
| [HLE w/o tools](/benchmarks/hlenotools) | 25.6% | [Ornith: Ornith 1.5 launch](https://ornith.ai/ornith_1_5.html) |

## Other Ornith AI Models

- [Ornith-1.5-397B](/models/ornith-1-5-397b) - Score: 62.72
- [Ornith-1.5-9B](/models/ornith-1-5-9b) - Score: 28.63