# Gemini 3.8 Flash (Google)

LLM, Google, reasoning low. Verbalized probabilities through the Jevals adapter, via OpenRouter · Google AI Studio.

| Board | Decision Score (95% range) | Rank | Accuracy | Calibration gap (ECE, pts) | Hand-off at 95% | $ per 1k decisions | Speed p95 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [noul (PubMedQA)](https://jevals.com/noul/) | 73.0 (62.1 to 82.2) | tied for rank 1 of 8 | 92.5% | 2.0 | 79% | $0.8 | 5.5 s |
| [choice (Banking77)](https://jevals.com/choice/) | 74.1 (68.4 to 79.8) | rank 1 of 8 | 84.6% | 3.2 | 45% | $1.4 | 3.9 s |
| [score (HelpSteer2 helpfulness)](https://jevals.com/score/) | 4.6 (−12.2 to 19.0) | tied for rank 1 of 8 | 42.4% | 22.6 | — | $1.3 | 4.0 s |

Decision Score: 100 = perfect, 0 = guessing the label base rates, below 0 = worse than that. Ranks: 1 + the number of rows significantly better (paired item bootstrap, 95%); rows that cannot be told apart share a rank. Hand-off at 95%: the share of decisions a model can take alone, at its own confidence threshold, while staying at least 95% right.

Setup: model id google/gemini-3.8-flash; served as google/gemini-3.8-flash; adapter jevals-llm 0383a0e3e592; reasoning low (mandatory); temperature provider default; price as of 2026-09-18.

Compare: [Jev vs Gemini 3.8 Flash](https://jevals.com/compare/jev-vs-gemini-3.8-flash/)

Source: https://jevals.com/models/gemini-3.8-flash/ · release 2026-09-18, suite 0.1.0 · data (CC-BY-4.0): https://jevals.com/data/releases/2026-09-18/board.json · cite as: Jevals (jevals.com), release 2026-09-18, suite 0.1.0. CC-BY-4.0.