Unverified50% confidenceBenchmarkExact time
Kimi K3 improves by 9.7 points using OpenVLHarness.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedKimi K3 scored 77.8% on coding benchmarks, ahead of OpenAI's new model at approximately 77.6% and another competing product at approximately 76.8%.73% similarUnverifiedAccording to the documentation, Kimi K2.8 performs at a level comparable to K3 but has more efficient reasoning capabilities, supporting a 1-million-token context window, image and video input, and three reasoning modes: low, high, and max.70% similarUnverifiedOn the B300 benchmark, Kimi K3's new optimization solution on vLLM achieved a 2.2 to 2.8× throughput improvement compared to version v0.27.1.66% similarUnverifiedKimi K2.6 achieved a success rate of 7.5% on CAD World, OpenCUA achieved 1.5%, and two other models achieved a success rate of 0.66% similarUnverifiedKimi K3 includes two flagship versions: K3 Max and K3 Swarm Max.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073234API
curl https://kongchang.com/api/v1/knowledge/claims/1073234MCP
get_claim(id=1073234)