There's no scarcity of generative AI benchmarks designed to measure the efficiency and accuracy of a given mannequin on finishing varied useful enterprise duties — from coding to instruction following to agentic net searching and device use. However many of those benchmarks have one main shortcoming: they measure the AI's capability to finish particular issues and requests, not how factual the mannequin is in its outputs — how nicely it generates objectively appropriate info tied to real-world information — particularly when coping with info contained in imagery or graphics.
For industries the place accuracy is paramount — authorized, finance, and medical — the dearth of a standardized method to measure factuality has been a vital blind spot.
That adjustments right this moment: Google’s FACTS group and its information science unit Kaggle launched the FACTS Benchmark Suite, a complete analysis framework designed to shut this hole.
The related analysis paper reveals a extra nuanced definition of the issue, splitting "factuality" into two distinct operational situations: "contextual factuality" (grounding responses in offered information) and "world information factuality" (retrieving info from reminiscence or the net).
Whereas the headline information is Gemini 3 Professional’s top-tier placement, the deeper story for builders is the industry-wide "factuality wall."
Based on the preliminary outcomes, no mannequin—together with Gemini 3 Professional, GPT-5, or Claude 4.5 Opus—managed to crack a 70% accuracy rating throughout the suite of issues. For technical leaders, it is a sign: the period of "belief however confirm" is much from over.
Deconstructing the Benchmark
The FACTS suite strikes past easy Q&A. It’s composed of 4 distinct checks, every simulating a special real-world failure mode that builders encounter in manufacturing:
Parametric Benchmark (Inner Data): Can the mannequin precisely reply trivia-style questions utilizing solely its coaching information?
Search Benchmark (Software Use): Can the mannequin successfully use an internet search device to retrieve and synthesize dwell info?
Multimodal Benchmark (Imaginative and prescient): Can the mannequin precisely interpret charts, diagrams, and pictures with out hallucinating?
Grounding Benchmark v2 (Context): Can the mannequin stick strictly to the offered supply textual content?
Google has launched 3,513 examples to the general public, whereas Kaggle holds a non-public set to stop builders from coaching on the take a look at information—a typical situation often known as "contamination."
The Leaderboard: A Recreation of Inches
The preliminary run of the benchmark locations Gemini 3 Professional within the lead with a complete FACTS Rating of 68.8%, adopted by Gemini 2.5 Professional (62.1%) and OpenAI’s GPT-5 (61.8%).Nevertheless, a better have a look at the information reveals the place the actual battlegrounds are for engineering groups.
Mannequin | FACTS Rating (Avg) | Search (RAG Functionality) | Multimodal (Imaginative and prescient) |
Gemini 3 Professional | 68.8 | 83.8 | 46.1 |
Gemini 2.5 Professional | 62.1 | 63.9 | 46.9 |
GPT-5 | 61.8 | 77.7 | 44.1 |
Grok 4 | 53.6 | 75.3 | 25.7 |
Claude 4.5 Opus | 51.3 | 73.2 | 39.2 |
Information sourced from the FACTS Group launch notes.
For Builders: The "Search" vs. "Parametric" Hole
For builders constructing RAG (Retrieval-Augmented Technology) methods, the Search Benchmark is essentially the most vital metric.
The information exhibits an enormous discrepancy between a mannequin's capability to "know" issues (Parametric) and its capability to "discover" issues (Search). As an illustration, Gemini 3 Professional scores a excessive 83.8% on Search duties however solely 76.4% on Parametric duties.
This validates the present enterprise structure commonplace: don’t depend on a mannequin's inner reminiscence for vital information.
In case you are constructing an inner information bot, the FACTS outcomes counsel that hooking your mannequin as much as a search device or vector database shouldn’t be non-compulsory—it’s the solely method to push accuracy towards acceptable manufacturing ranges.
The Multimodal Warning
Essentially the most alarming information level for product managers is the efficiency on Multimodal duties. The scores listed here are universally low. Even the class chief, Gemini 2.5 Professional, solely hit 46.9% accuracy.
The benchmark duties included studying charts, decoding diagrams, and figuring out objects in nature. With lower than 50% accuracy throughout the board, this implies that Multimodal AI shouldn’t be but prepared for unsupervised information extraction.
Backside line: In case your product roadmap includes having an AI mechanically scrape information from invoices or interpret monetary charts with out human-in-the-loop overview, you might be possible introducing vital error charges into your pipeline.
Why This Issues for Your Stack
The FACTS Benchmark is prone to change into a normal reference level for procurement. When evaluating fashions for enterprise use, technical leaders ought to look past the composite rating and drill into the particular sub-benchmark that matches their use case:
Constructing a Buyer Help Bot? Take a look at the Grounding rating to make sure the bot sticks to your coverage paperwork. (Gemini 2.5 Professional really outscored Gemini 3 Professional right here, 74.2 vs 69.0).
Constructing a Analysis Assistant? Prioritize Search scores.
Constructing an Picture Evaluation Software? Proceed with excessive warning.
Because the FACTS group famous of their launch, "All evaluated fashions achieved an general accuracy under 70%, leaving appreciable headroom for future progress."For now, the message to the {industry} is obvious: The fashions are getting smarter, however they aren't but infallible. Design your methods with the idea that, roughly one-third of the time, the uncooked mannequin would possibly simply be incorrect.
