TellWell
← Back to feed
Publications3h ago92% confidenceConfidence 92% — the share of independent, credible sources corroborating the core facts.

New Benchmark 'Agents' Last Exam' Measures AI Performance on Real-World Professional Tasks

Center 100%
1 source

Researchers have introduced Agents' Last Exam (ALE), a new benchmark designed to evaluate AI agents on long-horizon, economically valuable real-world tasks developed with 250+ industry experts. The benchmark covers 1,000+ tasks across 13 industry clusters and 55 sub-fields, revealing that current AI systems achieve below 1% full pass rates on the hardest tier. The benchmark aims to bridge the gap between strong performance on traditional benchmarks and actual economic deployment in professional domains.

Agents' Last Exam (ALE) is a newly introduced benchmark that addresses what researchers identify as a critical evaluation gap: while AI systems perform well on existing benchmarks, these gains have not translated into meaningful economic deployment across professional sectors. Developed collaboratively with over 250 industry experts, ALE evaluates AI agents on long-horizon tasks with verifiable outcomes across non-physical industries defined using the U.S. federal occupational taxonomy (O*NET/SOC 2018). The benchmark organizes 1,000+ tasks into 13 industry clusters spanning 55 sub-fields. Current testing across mainstream configurations shows that the most difficult tier remains far from saturated, with average full pass rates below 1%. The benchmark is designed as a living system that continuously expands as new workflows and industries are onboarded, positioning itself not as another leaderboard but as a tool for measuring progress toward economically meaningful AI impact.

What different sources said

Related

PublicationsConfidence 78% — the share of independent, credible sources corroborating the core facts.

Topology-Aware Thermodynamics Improves DNA Probe Specificity Design

Researchers developed a new framework for designing DNA probes that accounts for the spatial organization of matched sequences, not just overall thermodynamic stability. Traditional methods rely on scalar measures like melting temperature and free energy, which miss how mismatches are distributed along the probe. The approach could improve diagnostic accuracy in applications like HPV detection and gene expression profiling.

1 source2h ago
PublicationsConfidence 82% — the share of independent, credible sources corroborating the core facts.

Study Identifies Optimal Thermal Dose for Combining Focused Ultrasound with Immunotherapy in Tumors

Researchers used multimodal PET imaging to identify an optimal thermal dose range for focused ultrasound ablation that destroys tumor tissue while preserving conditions for immunotherapy delivery. The study found that excessive heating collapses blood vessels needed for antibody access, while insufficient heating fails to adequately reduce tumor burden. The findings could guide clinical design of combination treatments pairing thermal ablation with immunotherapies.

1 source3h ago
PublicationsConfidence 88% — the share of independent, credible sources corroborating the core facts.

Plant MSH1 Protein Functions as Mismatch-Directed Nuclease for Organelle Genome Maintenance

Researchers have identified the precise mechanism by which the AtMSH1 protein in Arabidopsis plants recognizes and cleaves DNA mismatches and lesions, preventing mutations in organellar genomes. The protein combines a DNA mismatch recognition module with a nuclease domain that makes staggered cuts at specific positions relative to DNA damage. This discovery explains how plants maintain unusually low mutation rates in their mitochondrial and chloroplast DNA compared to other eukaryotes.

1 source3h ago