RLTasksby ulam.ai
Models / Kimi

Kimi / MODEL EVIDENCE

Kimi K2 Instruct (0905)

2 benchmarks · 2 observations · 2 sources · released 2025-09-05

Scores at a glance

2 benchmarks · large dot: Kimi K2 Instruct (0905); small dots: closest models where reported

ForecastBench ↗62.7 Brier index
46.467

kimi-k2-instruct-0905† · Overall difficulty-adjusted Brier index ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

There are not enough shared scored settings to identify close comparisons reliably.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Forecastbench — methodology and published results ↗

    Epoch AI · 2026

  2. Fiction.liveBench — March 14, 2025 benchmark release ↗

    Fiction.live · 2025

Names used in source tables

Kimi K2 Instruct (0905) · kimi-k2-instruct-0905†