JOpen-Jev-27B-v1.1Recorded model outputs · Edited playback
Open-Jev-27B-v1.1 / New model + new demo

Same preview.
Different target.

The preview points to record_A. A candidate action now targets record_B. Inspect how two saved 27B v1.1 predictions select among the supplied options.

Get Open-Jev-27B-v1.1 ↗Get v1.1 data ↗Explore the code ↗

Rank-8 LoRA adapter + FP32 decision head over a pinned Qwen3.8-27B base. Base weights are required separately.

Illustrative UI from synthetic text-state records. No browser actions executed. Playback is edited and does not measure inference latency.

Public JevBench / 231 tasks

80 out of 111 on Hard.
One answer behind Jev.

Open-Jev-27B-v1.1 scores 197/231 overall (85.28%) and 80/111 Hard (72.07%). Jev scores 200/231 overall and 81/111 Hard.

This is the public 231-task subset of the 534-task benchmark. Model scale, data and prior training differ across Open-Jev versions. Shared multi-GPU evaluation times do not establish single-GPU or HTTP/API latency.

Public JevBench Hard comparison: Open-Jev-2B 46/111, Open-Jev-9B 66/111, Open-Jev-27B-v1.1 80/111, Jev 81/111. Overall 27B 197/231 and Jev 200/231.
127,787Complete internal Test/OOD rows audited
96.65%Expanded Test · 41,357 / 42,789 hard labels
96.44%Expanded OOD · 80,934 / 83,924 hard labels

All 43,301 Test and 84,486 OOD rows were evaluated; accuracy uses hard labels. The public dataset is a 326,619-row redistributable projection, excluding 2,053 Wiki records. It is not the complete internal corpus. See all four old/expanded Test/OOD columns · Audit and protocol.

New / Four interactive game demos

Your move. Then the model's.

Try Snake, tic-tac-toe, Box Runner and Tile Platformer. Choose an action, then inspect the real Open-Jev-27B-v1.1 probabilities across 16 independent recorded game states, including three model/reference disagreements.

Interactive snapshots of saved decisions; no live model inference or new gameplay rollout.

Enter the game arcade ↗
Try text classification in your browser

Bring your own categories.

The interactive workbench runs Open-Jev-2B on CPU. Paste messages or import a CSV, define labels, then download the results.

Open the Open-Jev-2B workbench ↗

Inspect the decision. Build your own.

Open-Jev-27B-v1.1 is a LoRA adapter and decision head. These selected examples do not establish a general task success rate or a safety guarantee.

27B v1.1 model ↗Code ↗Data ↗Project website ↗