GenomeQA (Binary Choice) - Splice Site Identification: leaderboard

GenomeQA (2026) tests general-purpose LLMs on raw DNA sequences with questions from biological databases in six task families: enhancer and promoter identification, splice sites, taxonomy, histone marks, transcription factor binding sites and motifs. This board is accuracy in percent on the two-option splice site identification questions, with thinking enabled where supported; higher is better, and chance is 50.

Metric: Accuracy (%) on the two-option (chance 50) Splice Site Identification questions of GenomeQA (raw DNA sequences as input), one fixed system prompt, thinking enabled where supported; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 6 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.1Thinking54.4#240
2Claude Sonnet 4.5Thinking53.2#261
3Gemini 3 Pro (Preview)50#119
4Llama 4 Maverick Instruct50#1157
5Qwen 3 Max (Preview)Thinking49.8#454
6Grok 4.1 FastReasoning47.6#427

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=genomeqa-binary-choice-splice-site-identification · How It Works · Data refreshed daily, snapshot 2026-11-21.