Skip to content
Trending storyDeveloping

vLLM reports Kimi K3.1 Pro scores 61.2% on Kimi Code Bench 3.0 Long-horizon

2 articles1 sourcesince Nov 4Last article 37m ago ·

Overview

AISummary of 2 articles

vLLM reports that Moonshot AI's K3.1 Pro scores 61.2% on Kimi Code Bench 3.0 Long-horizon, up from 55.95% for K3.

The internal benchmark covers multi-step execution, tool use, and end-to-end engineering. vLLM says both results were measured with the Claude Code harness at maximum reasoning effort.

The figures come from vLLM posts on X, and the benchmark is internal to Moonshot AI, so the scores have not been independently verified.

Written by AI from the articles below · updated Nov 4, 11:48 AM ET

Check the sources:

Latest developmentNov 4, 11:39 AM ET
Kimi K3.1 Pro scores 61.2% on Kimi Code Bench 3.0 long-horizon tasks

Article timeline

The articles in this story. Times are ET.

Nov 4
  1. vLLMOfficial
    Kimi K3.1 Pro scores 61.2% on Kimi Code Bench 3.0 long-horizon tasks

    AIMoonshot AI's K3.1 Pro scores 61.2% on Kimi Code Bench 3.0 Long-horizon, up from K3's 55.95%, according to a post from vLLM. The internal benchmark covers multi-step execution, tool use and end-to-end engineering, and both coding results use the Claude Code harness at maximum reasoning effort.

    Image from @vllm_project's post
  2. vLLMOfficial
    vLLM reports K3.1 Pro scores 61.2% on Kimi Code Bench 3.0 Long-horizon

    AIvLLM reports that Moonshot AI's K3.1 Pro scores 61.2% on the internal Kimi Code Bench 3.0 Long-horizon benchmark, up from K3's 55.95%. The benchmark covers multi-step execution, tool use, and end-to-end engineering. Both coding results were measured with the Claude Code harness at maximum reasoning effort.

    Image from @vllm_project's post

Heat Trend

Not enough continuous observations to show a trend yet.