Checked fact 286826 Oct 2026Models and releases

NVIDIA Research's Flora benchmark table lists Flora at 40.0 and GPT-6 Astra at 55.4 on RoboReward MAE (lower is better), and Flora at 64.7 against GPT-6 Astra's 77.4 on WGO-Bench gold-window accuracy (higher is better). The benchmarks are NVIDIA's own.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

RoboReward MAE 40.0 vs 55.4; WGO-Bench gold-window accuracy 64.7 vs 77.4 (Flora vs GPT-6 Astra)

What the source said when we opened it, on 26 Oct 2026.

The source

Flora: a data engine for labeling human and robot video
NVIDIA Research (GEAR lab)

Open the source archived copy

Checked

Checked by the notis newsroom on 26 Oct 2026, against the source above.

In the story

NVIDIA says its Flora data engine labels 200,000 hours of video a day on 512 GB300 GPUs. 26 Oct 2026

Cite this fact

Short permanent address

In a sentence

“NVIDIA Research's Flora benchmark table lists Flora at 40.0 and GPT-6 Astra at 55.4 on RoboReward MAE (lower is better), and Flora at 64.7 against GPT-6 Astra's 77.4 on WGO-Bench gold-window accuracy (higher is better). The benchmarks are NVIDIA's own.” ai notis, checked 26 Oct 2026. Source: Flora: a data engine for labeling human and robot video (NVIDIA Research (GEAR lab)). https://ainotis.com/c/2868

As a reference (APA style)

ai notis. (2026, October 26). NVIDIA Research's Flora benchmark table lists Flora at 40.0 and GPT-6 Astra at 55.4 on RoboReward MAE (lower is better), and Flora at 64.7 against GPT-6 Astra's 77.4 on WGO-Bench gold-window accuracy (higher is better). The benchmarks are NVIDIA's own [Checked claim 2868]. ai notis. https://ainotis.com/c/2868

Anyone may quote this address. It does not change; if we correct the story, this page says so.