Model profile
Gemini 2.0 Pro Exp 02 05
2eval lineages
Evidence summary
Published evidence spans 2 evals and 1 of 7 behavior components. Its strongest relative result is Confabulations (confabulation_rate, #16 of 52); its weakest is MASK (lying_probability_pct, #44 of 53).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model documentation ↗Family-level model document · google · first party
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| Confabulationsconfabulation_rate | #16 / 52 | 15.84 | ↓ lower | Source ↗official | |
| MASKlying_probability_pct | #44 / 53 | 51.33 | ↓ lower | Source ↗official |