alphaXiv Launches OpenResearch Intelligence Index, First Open Benchmark for Autoresearch
togethercompute · x · 2026-11-21
alphaXiv and Together AI launched the OpenResearch Intelligence Index, claimed to be the first open source composite benchmark for end-to-end autoresearch.
- Design: $7.4k in tokens across 8 models, 6 providers, 3 tracks — scientific knowledge (20 hand-picked Terminal-Bench-Science tasks), post-training ability (6 novel tasks), and literature relevancy/taste (PaperFindingBench subset), each model running in its native harness inside OpenResearch.
- Pain points addressed: poor "research taste" in current models, difficulty tracking evolving research goals, and black-box observability of research agents.
- Results (including Opus 5) are live; the benchmark is open source.
More from Models
- Waddle-1 robot-use agent scores 81 on unseen bimanual tasks, beating GPT-6.2 Astra at 66 — ycombinator · 2026-11-21
- AI Posts Math Results on Navier–Stokes and Riemann Hypothesis — While We Still Call LLMs Parrots — haider1 · 2026-11-21
- 26.4B Inkling 2 Mini matches 975B model in 128 days, ~17x compute efficiency gain — teortaxesTex · 2026-11-21
- Coding images of France with 6.2 Astra: a stress test for visual reasoning — prd_008 · 2026-11-21
- Hyperstition introduces judge-time scaling: a new scaling law for RL — eliebakouch · 2026-11-21
- Downdetector reports OpenAI outage starting 3:13 PM EST as user complaints pile up — VoidStateKate · 2026-11-21