Verdict
Claude Sonnet 4.6 leads 11–3 across 15 shared benchmarks.
Claude Sonnet 4.6 11 · Kimi K2.5 3 · 1 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Math: Claude Sonnet 4.6 leads 2–1 across 3 shared math benchmarks (largest gap: FrontierMath-2025-02-28-Private, 56.84 vs 48.95 — single evaluator).
Reasoning: Kimi K2.5 leads 2–1 across 3 shared reasoning benchmarks (largest gap: ARC-AGI, 86.5 vs 65.33 — protocols undisclosed).
Agentic: Claude Sonnet 4.6 leads 2–0 across 2 shared agentic benchmarks (largest gap: APEX-Agents, 23.7 vs 14.4 — protocols undisclosed).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
No vendor claims on file for Claude Sonnet 4.6.
Agentic / Tool Use
“It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.”
“K2.5 transitions from single-agent scaling to a self-directed, coordinated swarm-like execution scheme.”
Coding
“K2.5 generates code from visual specifications (UI designs, video workflows) and autonomously orchestrates tools for visual data processing.”
Multimodal
“Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.”
Claude Sonnet 4.6 leads 11–3 across 15 shared benchmarks. Claude Sonnet 4.6 leads 11 benchmarks and Kimi K2.5 leads 3, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Sonnet 4.6 and Kimi K2.5 have 15 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Sonnet 4.6 leads agentic 2–0. Claude Sonnet 4.6 leads math 2–1.