Unverified50% confidenceBenchmarkExact time
With two to three attempts, GLM-5.3 Flash scored 82%, which is within the margin of error of GPT-5.6 Luna's 81%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/6/2026
First Seen
Valid until: 10/20/2026
Sources
Related Entities
Related Claims
UnverifiedThe top-ranked models in single-turn tests are GLM-5.3 with a score of 96.2%, Kimi at 93.9%, and GLM-Flash at 92.2%, with all three achieving a raw score of 79/84.77% similarUnverifiedOn a three-sample math problem, DeepSeek V4.1 Flash scored 74 points, on par with Opus 5.0 and surpassing GLM's 67 points and V4 Pro's 62 points.74% similarUnverifiedOn Artificial Analysis's Omniscience hallucination metric, GPT-5.6 Sol Max reached 89%, higher than Claude Fable's 55% and GLM 5.2's 28%.74% similarUnverified在Terminal Bench 2.1基准测试上，GPT-5.6 Sol的Ultra模式接近92%，超越竞品的88%表现72% similarUnverifiedAt ultra-high reasoning intensity, GPT-6.1 Sol's factual error rate is 4.1%, lower than the previous generation's 4.5% and close to Astra's 4.0%.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980436API
curl https://kongchang.com/api/v1/knowledge/claims/980436MCP
get_claim(id=980436)