Agent benchmark
Part of Evaluation and benchmarking
Agent benchmark is gaining ground in AI research: 1.4% to 1.6% of new AI papers, +0.2 points. It ranks #1 of 214 by gain in share. As of Oct 10, 2026.
- Change in share
- +0.2 pts
- Share, last 3 months
- 1.6%
- Papers, last 3 months
- 533
- Ready for products
- 2.4 / 5
More in Evaluation and benchmarking
Counterfactual evaluation0.1% → 0.2%+0.1 ptsVision language model evaluation0.2% → 0.3%+0.1 ptsSoftware engineering benchmark0.2% → 0.3%+0.1 ptsLLM as a judge0.3% → 0.4%+0.1 ptsMultilingual evaluation0.2% → 0.3%+0.0 ptsMulti turn dialogue evaluation0.1% → 0.1%+0.0 ptsFaithfulness evaluation0.1% → 0.1%+0.0 ptsLLM safety evaluation0.1% → 0.1%+0.0 ptsVideo generation evaluation0.1% → 0.1%+0.0 ptsReference free evaluation0.1% → 0.1%+0.0 pts
Companies working on it
Agent benchmark: quick answers
Yes. Its share of new AI papers went from 1.4% to 1.6%, with 533 papers in the last 3 months.