Ensemble: Qwen 3.8 Flash (Althing), Sonnet 4 (Althing), DeepSeek V4.1 Flash, Gemini 2.5 Flash-Lite
ensemblesubpop_ensemble_complementary-4_20261014_122757
Configuration
- Framework
- ensemble
- Base provider
- —
- Model
- complementary-4
- Dataset
- subpop
- Temperature
- default
- Reasoning effort
- default
- Template
- current
- Samples/question
- —
- Timestamp
- 2026-10-14T12:27:57Z
Aggregate scores
Loading scores…
Per-question detail
| Question | Topic | Model modal | Human modal | JSD | |
|---|---|---|---|---|---|
| Loading per-question detail… | |||||
Could not load run data.