Unverified50% confidenceFactExact time
The 98% score claimed by Bonsai 2 is the average measured across 20 benchmarks with the thinking feature set to maximum intensity.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/4/2026
First Seen
Valid until: 1/2/2027
Sources
Related Entities
Related Claims
UnverifiedOn the simplest items, the behavioral test overestimates faithfulness by as much as 20 percentage points.72% similarUnverifiedThe composite score in this study places 80% weight on the large language model's judgment of factual entailment and 20% on lexical overlap.70% similarUnverifiedThe official claim is that Bonsai 2 can retain over 98% of FP16 performance on the Top-1 metric.67% similarUnverifiedThe 98% score from a single classification is the confidence level for that message's corresponding category, and does not represent an overall model accuracy of 98%.67% similarUnverifiedThe pLDDT score ranges from 0 to 100; scores above 90 are generally considered high-confidence predictions, 70–90 are considered good predictions, and scores below 50 should be interpreted with caution.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973448API
curl https://kongchang.com/api/v1/knowledge/claims/973448MCP
get_claim(id=973448)