// BENCHMARK

FinSearchComp-T3 benchmark

AI model leaderboard for the FinSearchComp-T3 benchmark. Compare how large language models score on FinSearchComp-T3, see the full ranking, and understand what this AI benchmark measures. Kimi K2 Thinking currently leads with 47.4. Financial-domain agentic search benchmark — Tier-3 difficulty subset on multi-source financial QA.

Leaderboard

# Model Organization Score Variant Source
#1 Kimi K2 Thinking Moonshot 47.4 thinking-w-tools official ↗
#2 Kimi K2 Moonshot 10.4 k2-0905-w-tools-cited-k2-thinking official ↗

Frequently asked questions about FinSearchComp-T3

What is the FinSearchComp-T3 benchmark?

Financial-domain agentic search benchmark — Tier-3 difficulty subset on multi-source financial QA.

How is the FinSearchComp-T3 benchmark scored?

FinSearchComp-T3 is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on FinSearchComp-T3?

As of the latest reported scores on GenAIList, Kimi K2 Thinking achieves the highest result on FinSearchComp-T3 with a score of 47.4.

Is a higher FinSearchComp-T3 score better?

Yes. On FinSearchComp-T3 a higher score indicates better performance, so models near the top of the leaderboard are the strongest.