Data as of November 11, 2026 · How the score is built
Released Nov 11, 2026262K contextGemini API model documentation
Gemini Decision 1
Decision readingGemini Decision 1 is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Nov 11, 2026 — see all recent releases
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Decision-system
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gemini-decision-1Google Gemini Decision model documentation
- Context window
- 262KGoogle Gemini Decision model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, video, audio, pdfGoogle Gemini Decision model documentation
- Output modalities
- calibrated decision probabilitiesGoogle Gemini Decision model documentation
- Parameters
- Not disclosed by the provider
- Availability
- Gemini API Decisions endpoint · Google AI StudioGoogle Gemini Decision model documentation
- Cloud regions
- Not tracked yet
- Lifecycle
- activeGoogle Gemini Decision model documentation
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordGoogle Gemini API pricing
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Gemini Decision 1, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Gemini Decision 1 is a proprietary model with a 262K context window. No explicit reasoning mode is documented in this profile.
Available on the Gemini API (v1beta Decisions endpoint) and in Google AI Studio, on the Free tier and the paid tier at $0.10 per million input tokens. Also listed on the Vercel AI Gateway. Thinking, caching and the Batch API are not supported.
Google released Gemini Decision 1 on November 11, 2026, with the Gemini Decisions API. It evaluates up to 1,000 typed questions (yes/no, single-select over 2 to 255 options, and rubric scores over 2 to 255 levels) over text, images, video, audio and PDFs in one forward pass, and returns calibrated probabilities and a confidence score with zero output tokens. Shared input runs up to 262,144 tokens; Google reports 150 to 250 ms end-to-end latency. Google-reported results (top-1 accuracy unless noted): JevBench public split 92.2%, Amazon ESCI macro-F1 58.7%, New Yorker Caption (text-only) 79.7%, Mind2Web Multimodal 86.2%, PubMedQA 79.8%, Global-MMLU-Lite (non-English) 86.0%, When2Call 79.9%, MMAU 71.8%, Video-MME (no subtitles) 69.1%, and a top-1 expected calibration error of 0.0250 across seven shared evals, against TypeSafe Jev 1.14, GPT-6 Luna and Gemini 3.5 Flash-Lite. These are provider-run results, kept here and off JevBench and general rankings.
The profile has no source-displayable benchmark row yet.
Last updated November 11, 2026. Runtime fields remain blank until a sourced snapshot exists.
Ask your AI, from current BenchLM data
Where does Gemini Decision 1 rank right now, and what does it cost?
Questions
How does Gemini Decision 1 perform overall in AI benchmarks?
Gemini Decision 1 does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Does Gemini Decision 1 have full benchmark coverage on BenchLM?
No. Gemini Decision 1 currently has 0 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Gemini Decision 1?
Gemini Decision 1 has a documented context window of 262K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.