Unverified50% confidenceBenchmarkExact time
After enabling reasoning mode, Grok 4.20's hard-to-verify injection score rose from 0.075 to 0.925 (nearly immune), but Qwen3-Next 80B Thinking only rose from 0.00 to 0.35, and the reasoning cost is 5 to 9 times that of non-reasoning.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedQwen3.8-27B achieves a pass@20 of 89.35% and an all-20 of 7.50% in ThinkingBox.69% similarUnverifiedIn the hard-to-verify category with injection bait, the number of questions for which GPT-5.4 mini judged incorrectly in both orderings rose from 3 to 39, Qwen3-Next 80B Instruct from 4 to 38, and GPT-5.4 mini and Qwen3-Next Instruct scored zero on hard questions (below the approximately 0.25 expected from random coin flipping).67% similarUnverifiedGrok 4.6的智能指数比Grok 4.5高5分，比Grok 4.3高23分66% similarUnverifiedExperience internalization fine-tuning improved Qwen3-8B-27B's one-shot score from 37.07 to 48.22, while reducing generated tokens from 6.41 million to 570,000 (an 11-fold reduction).65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/996781API
curl https://kongchang.com/api/v1/knowledge/claims/996781MCP
get_claim(id=996781)