Unverified50% confidenceBenchmarkExact time
Under the four-item weighted scoring rules, the final ranking is: GPT-6 Astra first (82.9), Claude Fable 5.1 second (80.1), DeepSeek V4.1 Flash third (71.5), GLM 5.3 fourth (68.9), Qwen 3.8 Max fifth (65.9), Gemini 3.8 Flash sixth (65.3), Grok 4.7 seventh (63.1), and Kimi K3 eighth (56.7).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/1/2026
First Seen
Valid until: 11/15/2026
Sources
2026 Large Model Benchmark Rankings: Where GPT-6, Claude, and Chinese AI Actually Differ
bilibili不管这么多10/14/2026
Related Entities
Related Claims
VerifiedOn the DeepSuite benchmark, Grok 4.7 scored 71%, GPT 5.6 Sol scored 72.7%, Fable 5.1 scored 70%, and Astra Max topped the leaderboard at 74.1%.75% similarUnverifiedIn automated benchmark tests, MiniMax M3.1 Flash scored 62%, Claude Opus 5 scored 50.3%, and GPT-5.6 Sol scored 45.8%.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1124536API
curl https://kongchang.com/api/v1/knowledge/claims/1124536MCP
get_claim(id=1124536)