Kimi K3 benchmark results

Alex Getman @alexgetmancom · 17 Jul 2026, 11:57 UTC · Updated 31 Oct 2026, 20:59 UTC

🚨 KIMI K3 JUST WRECKED THE BENCHMARKS

Took #1 in the frontend arena, broke into the top tier for general intelligence, and landed on the Pareto frontier for price-to-performance.

Fable isn’t retired yet, but someone should probably start drafting the paperwork.

Frontend Code Arena leaderboard chart showing Kimi-K3 ranked #1 with a score of 1,679, ahead of Claude Fable 5 and GPT-5.6 Sol.

Artificial Analysis Intelligence Index bar chart where Kimi K3 scores 57, placing it third behind Claude Fable 5 and GPT-5.6 Sol.

Pareto Frontier chart for Code Arena: Frontend showing Kimi K3 with a score of 1679 and price $12.00/M tokens at the top of the efficiency curve.

Fable 5 Kimi K3 Moonshot AI Kimi

Русская версия Markdown

Analysis

AI API pricing: calculate the cost of a finished task

23 OctOpen-weight model Kimi K3.1 Pro ranks second on the Artificial Analysis leaderboard

Kimi K3 Moonshot AI Kimi

23 OctKimi's benchmarks are absolutely mind-blowing. Is there a new sheriff in town?

Moonshot AI Kimi

23 OctKimi K3.1 Pro benchmarks are out! Of all these benchmarks, I trust Terminal-Bench 4.0 the most. And the results are impressive: Kimi K3.1 Pro scores 65.7, just 0.7 points behind the leader, Opus 5.5, while outperforming GPT-6 Astra by 7.5 points.

Kimi K3 Moonshot AI Kimi

23 Oct🚨 Kimi K3.1 is out now! Available outside China via Kimi Code. Pricing per 1M tokens: Input / Output: ~$2 / ~$10 I’ll post the benchmarks as soon as they’re available.

Kimi K3 Moonshot AI Kimi

KIMI K3 JUST WRECKED THE BENCHMARKS

Analysis

Related posts