NVIDIA's SpatialClaw accepted at NeurIPS, boosts GPT-6 and Opus 5 spatial reasoning
CMHungSteven · x · 2026-09-29
NVIDIA's SpatialClaw has been accepted to NeurIPS 2026. Using a single shared harness, it improves spatial reasoning across 20 benchmarks without model- or dataset-specific tuning: GPT-6 Astra rose from 71.3 to 77.4 (+6.1pp), Opus 5 gained +15.0 points, and GPT-6 Sol +11.7 — showing gains for both open-source and proprietary frontier models.
More from Research
- ZJU Releases EMem-Bench: 2,554 Episodes to Test Embodied Agent Memory — OmniAI-ZJU · 2026-09-29
- Tencent's AdaTutoRank Trains Setwise RAG Rerankers via Adaptive Tutoring Optimization — tencent · 2026-09-29
- Calibrated Importance Sampling Fixes Training-Inference Mismatch in LLM RLVR — Tianrun Yu · 2026-09-29
- Stanford lands $25M NIH grant to build AI center for personalized dementia care — StanfordAILab · 2026-09-29
- RL Gains May Hit a Wall: Verifiable Data Limits and Stalling nanochart Benchmarks — QuintinPope5 · 2026-09-29
- TALES Benchmark on LLM Game-Playing Accepted to NeurIPS 2026, New Results Coming — tw_killian · 2026-09-29