Mercury 2.5 (High): benchmark results

Provider: Inception. Released 2026-09-08. Access: API.

Aggregate Rating 1463 ± 31, rank #1271 of 2245 rated models, from 20 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Vals AI LegalBench83.06Accuracy (%)59.9
ObviousBench94.44Answer pass³ (%)55.7
Vals AI CyberBench45.48Accuracy (%)15.6
StudyArena Text - Weighted score1151Weighted score14.3
Vals AI MedCode31.33Accuracy (%)11.2
Vals AI Harvey Legal Agent Bench0Accuracy (%)10
Vals AI Vibe Code Bench3.68Accuracy (%)8.7
Vals AI Terminal-Bench 2.134.46Accuracy (%)6.7
Vals AI Public Benefits Bench45.26Accuracy (%)6
Vals AI Legal Research Bench4.33Accuracy (%)5.4
Vals AI Code Migration4.52Accuracy (%)5.1
Vals AI Finance Agent v218.89Accuracy (%)3.7

Interactive version: theaggregate.ai/model?slug=mercury-2-5-high · How It Works · Data refreshed daily, snapshot 2026-11-16.