@modal: Nova got Opus 4.8 to edge past Fable 5 on Terminal-Bench 2.1. Modal Sandboxes let the team decouple Nova’s agent loop a…

X AI KOLs Following News
ai-agents benchmark terminal-bench opus-4-8 modal agent-os

Summary

Nova reports that its Agent OS, built with Modal Sandboxes, pushed Claude Opus 4.8 to 83.9% on Terminal-Bench 2.1—edging out Fable 5's 83.8% without any fine-tuning, showing that agent orchestration can now rival frontier model capability.

Nova got Opus 4.8 to edge past Fable 5 on Terminal-Bench 2.1. Modal Sandboxes let the team decouple Nova’s agent loop and automatic review from tool execution, with fast startup and changes deployed in seconds to keep iteration quick. The result: 83.9%, up five percentage points from Opus 4.8’s Claude Code baseline and just ahead of Fable 5’s 83.8%.
Original Article
View Cached Full Text

Cached at: 10/30/26, 11:19 AM

Nova got Opus 4.8 to edge past Fable 5 on Terminal-Bench 2.1.

Modal Sandboxes let the team decouple Nova’s agent loop and automatic review from tool execution, with fast startup and changes deployed in seconds to keep iteration quick.

The result: 83.9%, up five percentage points from Opus 4.8’s Claude Code baseline and just ahead of Fable 5’s 83.8%.

Carl Hasselskog (@CarlHasselskog): We made Opus 4.8 perform like Fable 5.

Same model. No fine-tuning.

Terminal-Bench 2.1: Opus 4.8 in Claude Code: 78.9% Opus 4.8 in Nova Agent OS: 83.9% Fable 5: 83.8% Built together with our friends at @modal. The frontier isn’t only the model anymore.

Similar Articles

@robinebers: Fable 5 Low > Opus 4.8 Max

X AI KOLs Following

A user posts a comparison suggesting Fable 5 Low outperforms Opus 4.8 Max, with another user commenting that Fable 5 is back but being used incorrectly.