4.3K views · 20 likes · 1 reposts (at collection)
Artificial Analysis Finds Open Weights Models Rank Lower on Truthfulness
- Who
- Artificial Analysis
- What
- published a comparison of personality trait rankings for the top 10 open weights and 10 proprietary models
- When
- Quote
We compared the 10 open weights and 10 proprietary models measured with the highest Artificial Analysis Intelligence Index scores.
What happened
In AA-PersonalityBench, the 10 highest-scoring open weights models average lower ranks than the 10 highest-scoring proprietary models on truthfulness, pragmatism and structure, and higher on slop and bottom-line summaries. Models were ranked from 1 to 100 across 30 personality traits; the largest gap was on Truthful, where open weights averaged 47 versus 79 for proprietary models.
Read next
See the full storyArtificial Analysis Finds Different Personality Rankings for Open and Proprietary ModelsIn AA-PersonalityBench, the top open weights models on average rank lower than the top proprietary models on truthfulness, pragmatism and structure, and higher on slop and summarizing the bottom line
We compared the 10 open weights and 10 proprietary models measured with the highest Artificial Analysis Intelligence Index scores. Each model is percentile ranked from 1 to 100 on each of 30 personality traits. On average, the top open weights models rank 32 points lower than the top proprietary models on Truthful, the largest gap of any trait.
Average rank, top proprietary vs. top open weights:
➤ Open weights rank lower: Truthful (79 vs. 47), Pragmatic (79 vs. 49), Natural Sounding (77 vs. 52), Evidence-Based (76 vs. 47), Structured (73 vs. 45) and Literate (70 vs. 47)
➤ Open weights rank higher: Slop (30 vs. 49), Bottom-Line Summary (47 vs. 62) and Scannable (41 vs. 53)
The story so far
Artificial Analysis found that its 10 highest-scoring open weights models ranked lower on truthfulness, pragmatism and structure, and higher on slop and bottom-line summaries than its 10 highest-scoring proprietary models. The largest gap was on the Truthful trait: open weights models averaged rank 47, compared with 79 for proprietary models. The comparison covered models with the highest Artificial Analysis Intelligence Index scores in each group. Models were ranked from 1 to 100 across 30 personality traits.
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 · 2026-11-04