NCKI kspine_v3: leaderboard

NCKI kspine_v3 — Frozen bank/rung placement no-chain-of-thought benchmark; NCRI15.2 reasoning and NCKI kspine_v3 knowledge are separate native index scales, not percentages. Source chart eligibility flags are retained, never used as automatic filters. Explicit required filler configuration remains a source run. Metric: NCKI kspine_v3 index. Source: https://github.com/neelnanda-io/nocot-bench

Metric: NCKI kspine_v3 index. Source: github.com. Saturation forecast: Around December 2027. 285 models tracked. Updated 16 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-6 Astra131.08#6
2GPT-6.1 Sol129.56#10
3Gemini 4 Argon128.35#12
4Claude Fable 5.1128.32#15
5Claude Fable 5128.17#27
6Claude Opus 5.5125.67#5
7Gemini 3.1 Pro (Preview)121.37#93
8Gemini 3.7 Flash121.09#34
9Gemini 3.8 Flash120.61#36
10GPT-5.6 Sol120.59#30
11Claude Opus 5119.33#20
12GPT-6 Sol118.7#26
13Claude Opus 4.7118.41#78
14Claude Opus 4.8117.15#58
15Kimi K3.1 Pro116.3#29

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=ncki-kspine-v3 · How It Works · Data refreshed daily, snapshot 2026-11-16.