SecureBio ABLE Full: leaderboard

SecureBio ABLE Full — Native SecureBio benchmark panel; exact named population. Accuracy includes native refusal/failure conventions and source-reported runs. Raw fractions converted only according to this panel: ABLEFull already uses percent, baseline-only and other capability panels use fractions. Metric: Accuracy (%). Source: https://securebio.org/benchmarks/details/

Metric: Accuracy (%). Source: securebio.org. Saturation forecast: Around February 2027. 20 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.1 Pro (Preview)High84.62#93
2GPT-5.5 ProxHigh83.57#35
3Kimi K2.582.51#256
4Kimi K3Max78.43#56
5GLM-5.2Max76.68#141
6Gemini 3 Pro (Preview)High74.71#113
7Mistral Large 4High65.31#137
8Nemotron 3 Ultra62.52#428
9InklingxHigh59.94#281
10Inkling SmallxHigh57.5#299
11GPT-OSS-120B51.71#703
12Beam 1.0Max50.51#206
13Nemotron 3 Super49.06#775
14Kimi K2 (Thinking)48.12
15Qwen 3 235B A22BThinking45.2#628

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

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