G9v3-3B: benchmark results

Provider: AI9Stars. Released 2026-07-23. Access: Open.

Aggregate Rating 1423 ± 43, rank #5162 of 10516 rated models, from 22 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA-Omniscience Hallucination Rate11.66Hallucination Rate (%)99.8
AA Omniscience-4.37Score70.1
AA Long Context Reasoning41.33Accuracy (%)34.9
AA Omniscience - Software Engineering (SWE) - HTML20Accuracy (%)22
AA CritPt0Accuracy (%)20.6
AA Omniscience - Software Engineering (SWE) - Swift20Accuracy (%)20.5
AA Humanity's Last Exam4.49Accuracy (%)19.8
AA GPQA Diamond43.84Accuracy (%)19.2
AA Omniscience - Software Engineering (SWE) - C17Accuracy (%)15.5
AA Terminal-Bench 2.15.99Pass@1 (%)14
AA Omniscience - Software Engineering (SWE) - Julia0Accuracy (%)10.8
AA Omniscience - Software Engineering (SWE) - Rust24Accuracy (%)9

Interactive version: theaggregate.ai/model?slug=g9v3-3b · How It Works · Data refreshed daily, snapshot 2026-11-21.