Artificial Analysis Adds SubQ Snap 1.2 Results to Decision Index
Understand the event
Artificial Analysis reports that SubQ Snap 1.2 scored 73 on Decision Index v2.1, up from 68 for version 1.1 and within 0.1 points of Drex Max v1.1 and GLiDE v1.2. Its all-pass rate on AA-Paperclip rose from 46% to 62%. On AA-Omniscience-Decision and HLE-MultiChoice, non-hallucination rates improved while accuracy stayed at 21% and 9%, respectively; Artificial Analysis attributes those gains to abstention. The results build on Decision Index v2, which Artificial Analysis released with private datasets accounting for 45% of the index, up from 25% in v1. The updated Decision Score rewards both correct answers and calibrated confidence.
Generated by AI from reports · Updated 7 hours ago
Read next
More changes in today’s briefingGoogle Expands Antigravity Teamwork for Research and EngineeringDevelopments
2 developments
- 11/14 08:14 (UTC+8) · 1 reportsArtificial Analysis Ranks SubQ Snap 1.2 on Decision Index v2.1Artificial Analysis · X:SubQ Snap 1.2 Scores 73 on Artificial Analysis Decision Index v2.1
- 11/9 07:51 (UTC+8) · 1 reportsArtificial Analysis Releases Decision Index v2Artificial Analysis · X:Artificial Analysis Releases Decision Index v2 With New Benchmarks and a Calibration-Aware Score
Report timeline
Follow the reports to explore different sides of the event.
- SubQ Snap 1.2 Scores 73 on Artificial Analysis Decision Index v2.1
Artificial Analysis reports that SubQ Snap 1.2 scores 73 on its Decision Index v2.1, up from 68 for version 1.1 and within 0.1 points of Drex Max v1.1 and GLiDE v1.2. Its all-pass rate on AA-Paperclip rises from 46% to 62%. On AA-Omniscience-Decision and HLE-MultiChoice, non-hallucination rates improve while accuracy remains flat at 21% and 9%, respectively; the post attributes those gains to abstention.
- Artificial Analysis Releases Decision Index v2 With New Benchmarks and a Calibration-Aware Score
Artificial Analysis has released Decision Index v2, with 45% of the index now based on private datasets, up from 25% in v1. Its new Decision Score rewards both correct answers and calibrated confidence. Drex Max v1.1 and GLiDE v1.2 each score 73, while Mammoth 27B scores 72; the post also compares task costs and times across decision models and language models.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue
Event heat trend
- Current within comparable coverage
- 8
- Peak within comparable coverage
- 1011/14 09:00 (UTC+8)
- 24-hour change
- –
Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.