Grok Imagine Video 1.5 agent lands #5 on Text-to-Video Arena with 1491 pts, 3 pts behind leaders
jefffhj · x · 2026-09-06
xAI officially launched Grok Imagine Video 1.5 agent and entered the LMArena Text-to-Video Arena:
- Debuts at #5 with 1491 pts, just 3 points behind Wan-3.0 and FLUX 3 Video (both 1494).
- Outperforms Dreamina Seedance-2.5, Seedance-2.0, and MiniMax-H3.
- Powered by the new Image 2.0 model, with higher quality, smarter agent-driven storytelling, and notably better multi-shot continuity.
- The Arena team notes xAI is now a top-5 lab in text-to-video.
More from Multimodal
- Precise camera control and bullet time with Minimax-H3, single image input — init-5 · 2026-09-06
- Indie dev replaces $5k-$10k video project with Astra-generated video in two hours — jdjohnson · 2026-09-06
- AI filmmaker Sam Wasserman premieres short film "The Miracle" — DavidmComfort · 2026-09-06
- Mercor pays $23-54/hr for music experts to evaluate a leading AI lab's generative music models — menhguin · 2026-09-06
- Dev uses free models from OpenAI, Qwen, MiniMax and more to recreate TRON-style motherboards — jasonkneen · 2026-09-06
- MiniMax-H3 beats LTX 2.5 in creator's tests; ComfyUI workflow shared for dark fantasy short — SignalEquivalent9386 · 2026-09-06