Unverified50% confidenceBenchmarkExact time
On Cognition's Frontier Code 2.0, Mistral Large 4 leads at 19.7%; on the Artificial Analysis Coding Agent Index it scores 48%; the Cyber Index is 51%, with a malicious cyber refusal rate of 96.6%
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/31/2026
First Seen
Valid until: 11/14/2026
Sources
Mistral Large 4 Open Weights Released: Can a 1T-Parameter Model Run on Consumer Hardware?
youtubeScottek10/30/2026
Related Entities
Related Claims
UnverifiedEarly third-party benchmarks show Mistral Large 4 scoring 38 on the Intelligence Index, behind GLM 5.3's 45 and KIMI-K3's 44; its Cyber Index score is 50, and SciBench reaches 93%.78% similarUnverifiedAccording to the evaluation by the Artificial Analysis Coding Agent Index, Mistral Large 4 scored 48 points.77% similarUnverifiedMistral Large 4 achieved 61.7% on SWE Atlas Q&A, 28.3% on Terminal Bench, and 49.8% on the综合 Coding Agent Index.77% similarUnverifiedMistral Large 4 scored approximately 62% on the real-world software engineering benchmark DeepSwee.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1120222API
curl https://kongchang.com/api/v1/knowledge/claims/1120222MCP
get_claim(id=1120222)