Unverified50% confidenceBenchmarkExact time
On the Terminal-Bench 4.0 benchmark, Mistral Large 3 achieved a score of 65.2%, ranking second worldwide.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedOn the SWE-bench Verified benchmark, Mistral Large 3 achieved a score of 53.8%.77% similarUnverifiedMistral Large 4 scored approximately 62% on the real-world software engineering benchmark DeepSwee.71% similarUnverifiedMistral Large 4 在 AutomationBench（657 个业务流程）上得分 59.9%，在 AA-Briefcase 上获得 1393 Elo。70% similarUnverified在 Surge AI 组织的盲评中，专业标注员给 Mistral Large 4 预览版打出 3.74/5，在五个模型中排名第二，落后于 Claude Opus 5（4.22），领先于 GLM-5.3、Kimi K3 和 GLM-5.2。68% similarUnverifiedMistral Large 4 在网络安全基准 Cybench（40 个 CTF 挑战）上得分 93%，在漏洞复现与修补测试中得分 82%，在 B3 AI 安全基准上得分 93.3%。67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1008185API
curl https://kongchang.com/api/v1/knowledge/claims/1008185MCP
get_claim(id=1008185)