Reve 2.1
Reve·
LLMsimagecloud
Overview
Iteration on Reve's layout-first 4K text-to-image model, with improved prompt understanding, world knowledge and in-image text rendering (including foreign scripts). Retains the layout-as-prompt architecture and native 4K output.
Capabilities and innovations
Layout-first generationNative 4K (4096×4096) outputAddressable / editable elementsText rendering in imagesForeign-script text renderingLayout-as-prompt (position + size + local description)Native 4096×4096 output
Benchmarks
No benchmark values are recorded for this model.
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
- MMLU-Pro: not reported by the vendor
- Terminal-Bench 2.x: not reported by the vendor
- MMMU-Pro: not reported by the vendor
Links
More from Reve
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.