AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

LLM Stats

FACTS Grounding

A benchmark evaluating language models' ability to generate factually accurate and well-grounded responses based on long-form input context, comprising 1,719 examples with documents up to 32k tokens requiring detailed responses that are fully grounded in provided documents

Evaluation context and evidence

Source
LLM Stats
Publisher
Not recorded
Benchmark release
Not recorded
Collected
2026-08-17
Modality
text

These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.

Original sources

Reported results 13

Shown in source observation order, not ranked. Dates retain the precision provided by the source.

ModelValueUnitProtocolReported date and basisSource
Gemini 2.5 Pro Preview 06-050.878Not recordedNot recorded2025-06-05 · model_announcementLLM Stats
Gemini 2.5 Flash0.853Not recordedNot recorded2025-05-20 · model_announcementLLM Stats
Gemini 2.5 Flash-Lite0.841Not recordedNot recorded2025-06-17 · model_announcementLLM Stats
Gemini 2.0 Flash-Lite0.836Not recordedNot recorded2025-02-05 · model_announcementLLM Stats
Gemini 2.0 Flash0.836Not recordedNot recorded2024-12-01 · model_announcementLLM Stats
Gemma 3 12B0.758Not recordedNot recorded2025-03-12 · model_announcementLLM Stats
Gemma 3 27B0.749Not recordedNot recorded2025-03-12 · model_announcementLLM Stats
Gemini 3 Pro0.705Not recordedNot recorded2025-11-18 · model_announcementLLM Stats
Gemma 3 4B0.701Not recordedNot recorded2025-03-12 · model_announcementLLM Stats
Gemini 3 Flash0.619Not recordedNot recorded2025-12-17 · model_announcementLLM Stats
GLM-5V-Turbo0.586Not recordedNot recorded2026-04-02 · model_announcementLLM Stats
Gemini 3.1 Flash-Lite0.406Not recordedNot recorded2026-03-03 · model_announcementLLM Stats
Gemma 3 1B0.364Not recordedNot recorded2025-03-12 · model_announcementLLM Stats