Grok 4.7 enters AutoResearchExam live leaderboard, ranks No.3 at 30min and No.4 after 24h auto-research
AlexGDimakis · x · 2026-09-24
Grok 4.7 has been added to Bespoke Labs' live AutoResearchExam leaderboard: it jumps to No.3 at 30 minutes of auto-research, drops to No.4 at 4 hours, and lands at No.4 after the full 24-hour run. The author calls its performance/cost tradeoff "pretty good."
AutoResearchExam measures how well agents improve open-ended ML research tasks over 24 hours of auto-research, using hidden-test AUARC (Area Under the AutoResearch Curve) to combine solution quality, generalization, and speed, across 29 tasks. Key design points: one-shot evals miss iterative research dynamics, rankings shift with the evaluation time budget, and the benchmark also compares cost efficiency and how agents allocate research effort.
More from Models
- Do typos discomfort LLMs? Tokenization quirk sparks debate — menhguin · 2026-11-11
- MiniMax H3 hits 100 days open-source: 1,472 derivative models, 148M+ downloads — linoy_tsaban · 2026-11-11
- Meituan's LongCat-2.5 trends on Hugging Face as MoE multimodal model — meituan-longcat · 2026-11-11
- Fable 5.2 hands-on: great at well-defined hard problems, best since GPT 6 Astra — rachittshah · 2026-11-11
- The next AI vendor lock-in won't be the model API, it'll be the harness — Arindam_1729 · 2026-11-11
- Leaked: OpenAI's GPT-6.2 (codename betelgeuse) reportedly weighs in at ~15T tokens, drops Thursday — iruletheworldmo · 2026-11-11