Ensemble: Haiku 5.5 (Althing), Llama 3.3 70B, Gemini 2.5 Flash-Lite
ensembleopinionsqa_ensemble_complementary-mid_20261014_122751
Configuration
- Framework
- ensemble
- Base provider
- —
- Model
- complementary-mid
- Dataset
- opinionsqa
- Temperature
- default
- Reasoning effort
- default
- Template
- current
- Samples/question
- —
- Timestamp
- 2026-10-14T12:27:51Z
Aggregate scores
Loading scores…
Per-question detail
| Question | Topic | Model modal | Human modal | JSD | |
|---|---|---|---|---|---|
| Loading per-question detail… | |||||
Could not load run data.