---
type: "raw_signal"
id: "claude-opus-5-5-tops-vals-ai-s-e3da90"
slug: "claude-opus-5-5-tops-vals-ai-s-e3da90"
title: "Claude Opus 5.5 tops Vals AI's SWE-bench Multimodal at 70.21%, 9 points ahead of Claude Fable 5.1."
description: "## Event Vals AI’s SWE-bench Multimodal leaderboard, updated October 13, 2026, ranks Claude Opus 5.5 first with 70.21% accuracy. Claude Fable 5.1 follows at 61.25%, and Claude Sonnet 5.5 at 58.33%."
retrieval_nugget: "## Event Vals AI’s SWE-bench Multimodal leaderboard, updated October 13, 2026, ranks Claude Opus 5.5 first with 70.21% accuracy. Claude Fable 5.1 follows at 61.25%, and Claude Sonnet 5.5 at 58.33%."
observed_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "observed_at"
why_it_matters: "The benchmark covers 480 tasks from 11 repositories. Each task asks an agent to address a JavaScript software issue whose report depends on a screenshot or short recording, then grades the final code diff with repository tests. Vals AI says its published runs disable internet access because agents with general access can locate the upstream pull request containing the fix. Its page reports that cl"
novelty: "notable"
verification_level: "source-linked"
signal_type: "research"
source_platform: "vals.ai"
topics: ["claude"]
entities: ["Vals AI","SWE-bench Multimodal","Claude Opus 5.5","Claude Fable 5.1","Claude Sonnet 5.5","Anthropic"]
related_patterns: []
source_url: "https://www.vals.ai/benchmarks/swebench-multimodal"
source_urls: ["https://www.vals.ai/benchmarks/swebench-multimodal"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:claude-opus-5-5-tops-vals-ai-s-e3da90"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/claude-opus-5-5-tops-vals-ai-s-e3da90/","markdown":"https://newruntime.com/signals/claude-opus-5-5-tops-vals-ai-s-e3da90.md","json":"https://newruntime.com/signals/claude-opus-5-5-tops-vals-ai-s-e3da90.json"}
---

# Claude Opus 5.5 tops Vals AI's SWE-bench Multimodal at 70.21%, 9 points ahead of Claude Fable 5.1.

## Retrieval answer

## Event Vals AI’s SWE-bench Multimodal leaderboard, updated October 13, 2026, ranks Claude Opus 5.5 first with 70.21% accuracy. Claude Fable 5.1 follows at 61.25%, and Claude Sonnet 5.5 at 58.33%.

## Event
Vals AI’s SWE-bench Multimodal leaderboard, updated October 13, 2026, ranks Claude Opus 5.5 first with 70.21% accuracy. Claude Fable 5.1 follows at 61.25%, and Claude Sonnet 5.5 at 58.33%.

The benchmark covers 480 tasks from 11 repositories. Each task asks an agent to address a JavaScript software issue whose report depends on a screenshot or short recording, then grades the final code diff with repository tests. Vals AI says its published runs disable internet access because agents with general access can locate the upstream pull request containing the fix. Its page reports that closing network access reduced scores by 21–35 percentage points for three models compared in its diagnostic.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)