Unverified50% confidenceBenchmarkExact time
Among agent benchmarks, the top of both apex-agents and Long-Horizon-Terminal-Bench is moonshotai/Kimi-K3 (41 and 6 respectively), agents-last-exam belongs to XiaomiMiMo/MiMo-V2.6-Pro-RL (31.6), and Toolathlon is taken by the upgraded model of the same series, MiMo-V2.6-Pro-RL, with 76.9.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedXiaomi launched MiMo-V2.6 on Product Hunt, an open-source omnimodal model family designed for long-horizon agent tasks.65% similarUnverifiedThis benchmark was conducted on four model families — Gemma, Qwen, Kimi, and MiniMax — using AMD Instinct MI300X and MI355X hardware.65% similarUnverifiedOn the CyberGym benchmark, Mistral Large 4 scored 82, ranking first among all open-source models and surpassing MIMO, Grok, GLM 5.3, Kimi K3, and others.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1058240API
curl https://kongchang.com/api/v1/knowledge/claims/1058240MCP
get_claim(id=1058240)