# Ai2 finds frontier model accuracy drops to 13% on longest tasks

> Original title: We tested open pretrained models + frontier models incl. Gemini 3.8 Flash, Claude Opus 5.5, & GPT-6 Sol + Luna.

- Source: Ai2
- Published: 2026-11-03T17:28:38.000Z
- Bad Influence: https://badinfluence.news/items/ng3e9gdxkhmj96lq17x53aq6p
- Original: https://x.com/allen_ai/status/2117670297532797227

## Summary

Ai2 tested open pretrained models and frontier models, including Gemini 3.8 Flash, Claude Opus 5.5, and GPT-6 Sol and Luna. The frontier models performed well on simpler problems, but accuracy fell sharply as tasks grew harder and inputs longer, reaching 13% or lower on the longest general finite problems.

## Post

We tested open pretrained models + frontier models incl. Gemini 3.8 Flash, Claude Opus 5.5, & GPT-6 Sol + Luna.

Frontier models did well on simpler problems. But as tasks got harder & inputs longer, accuracy dropped sharply—to 13% or lower on the longest general finite problems.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWN54LwWwAAbnB6.jpg&mode=thumb&exp=1793923200&sig=068eb01ebc3c38a8)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWN54J3XUAA5aIR.jpg&mode=thumb&exp=1793923200&sig=ac1e82349b37ff48)