# BTL-3 benchmark scores

Other · model · https://benchgap.net/model/btl-3 · data retrieved 2026-11-21

As of 2026-11-21, BTL-3 (Other) has measured scores on 2 benchmarks and estimated scores on 11 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-SciCode](https://benchgap.net/b/aa-sci-code/current.md) | 46.4% | estimated ± 4.7 pp, high confidence |
| [GDPval-AA](https://benchgap.net/b/gdpvalaanormalized/current.md) | 38.6% | estimated ± 5.5 pp, low confidence |
| [LiveCodeBench v6](https://benchgap.net/b/livecodebench-v6/current.md) | 88.1% | measured |
| [SciCode](https://benchgap.net/b/scicode/current.md) | 49.3% | estimated ± 4.9 pp, high confidence |
| [τ²-bench results](https://benchgap.net/b/tau2-bench/current.md) | 100.0% | estimated ± 12.4 pp, low confidence |
| [AA Coding Index](https://benchgap.net/b/aa-coding-index/current.md) | 57.9% | estimated ± 5.7 pp, medium confidence |
| [SWE-bench Verified](https://benchgap.net/b/swe-bench-verified/current.md) | 73.5% | estimated ± 9.7 pp, low confidence |
| [BFCL v4](https://benchgap.net/b/bfcl-v4/current.md) | 88.5% | measured |
| [SWE-bench Pro](https://benchgap.net/b/swe-bench-pro/current.md) | 55.6% | estimated ± 6.0 pp, medium confidence |
| [Vals LiveCodeBench](https://benchgap.net/b/valslivecodebench/current.md) | 86.1% | estimated ± 3.4 pp, medium confidence |
| [MCP Atlas](https://benchgap.net/b/mcpatlas/current.md) | 75.5% | estimated ± 14.2 pp, low confidence |
| [NL2Repo](https://benchgap.net/b/nl2repo/current.md) | 41.1% | estimated ± 3.4 pp, high confidence |
| [PinchBench](https://benchgap.net/b/pinchbench/current.md) | 100.0% | estimated ± 5.0 pp, low confidence |
