# BTL-3 Benchmark Scores & Performance

> BTL-3 by Bad Theory Labs has 3 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/btl-3

Last updated: September 10, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Bad Theory Labs |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 262K |
| Official model card | [Bad Theory Labs BTL-3 model card](https://huggingface.co/badtheorylabs/BTL-3) |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: BTL
- Variant: base
- Benchmarks covered: 3 of 434
- Sibling models: [BTL-4](/models/btl-4), [BTL-4 Compact](/models/btl-4-compact)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [BFCL v4](/benchmarks/bfcl-v4) | 88.5% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [HumanEval](/benchmarks/humaneval) | 95.1% |
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 88.1% |

## Other Bad Theory Labs Models

- [BTL-4](/models/btl-4) - Score: not computed
- [BTL-4 Compact](/models/btl-4-compact) - Score: not computed
- [Macaw](/models/macaw-v1) - Score: not computed