---
type: "post"
id: "claude-opus-5-5-tops-vals-ai-s-3c4a0e"
slug: "claude-opus-5-5-tops-vals-ai-s-3c4a0e"
title: "Claude Opus 5.5 tops Vals AI's SWE-bench Multimodal at 70.21%, 9 points ahead of Claude Fable 5.1."
description: "Why this result is conditional Thesis Benchmark leadership is meaningful only alongside the environment that produced it. Vals AI’s October 13 2026 leaderboard places Claude Opus 5.5 first on SWE-bench Multimodal at 70.21 ahead of Claude Fable 5.1 at 61.25"
retrieval_nugget: "Why this result is conditional Thesis Benchmark leadership is meaningful only alongside the environment that produced it. Vals AI’s October 13 2026 leaderboard places Claude Opus 5.5 first on SWE-bench Multimodal at 70.21 ahead of Claude Fable 5.1 at 61.25"
published_at: "2026-10-14"
updated_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "published_at"
topics: ["claude"]
source_urls: ["https://www.vals.ai/benchmarks/swebench-multimodal"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:claude-opus-5-5-tops-vals-ai-s-3c4a0e"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:c7f72e13864f914d6d0fed2d75828d7bc8f12892bc4a4e93e86e927b058b83ed","reviewed_at":"2026-10-14T08:02:53.104Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Benchmark leadership is meaningful only alongside the environment that produced it.","observed_facts":[{"text":"Vals AI's leaderboard updated October 13, 2026 ranks Claude Opus 5.5 first at 70.21%, ahead of Claude Fable 5.1 at 61.25%.","source_urls":["https://www.vals.ai/benchmarks/swebench-multimodal"]},{"text":"The benchmark contains 480 tasks from 11 repositories; issues depend on screenshots or short recordings.","source_urls":["https://www.vals.ai/benchmarks/swebench-multimodal"]},{"text":"Vals AI says published runs disable internet access and reports a 21–35 percentage-point network-access effect for three models in its diagnostic.","source_urls":["https://www.vals.ai/benchmarks/swebench-multimodal"]}],"mechanism":"An agent receives the issue and image, works in a shell, and its final diff is graded using repository tests. Vals AI says every published run has no internet access because instance identifiers make the upstream pull request easy to find; agents with general access can copy the fix.","why_now":"The current leaderboard makes this constraint salient, and the page’s diagnostic reports a 21–35 percentage-point drop when network access was removed for three models.","implications":["Teams evaluating coding agents should match benchmark conditions to their own access controls and task inputs before treating rank as a deployment forecast."],"evidence_boundary":"These are leaderboard results reported by Vals AI, with each model run once; they do not establish comparative performance across all coding work or repeated-run variability.","watch_conditions":["Watch for repeated runs and disclosed uncertainty on this task set, plus comparable results under explicitly stated network-access conditions."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied for this benchmark result, so this is a distinct record centered on its leaderboard and evaluation conditions."}
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/posts/claude-opus-5-5-tops-vals-ai-s-3c4a0e/","markdown":"https://newruntime.com/posts/claude-opus-5-5-tops-vals-ai-s-3c4a0e.md","json":"https://newruntime.com/posts/claude-opus-5-5-tops-vals-ai-s-3c4a0e.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

Why this result is conditional Thesis Benchmark leadership is meaningful only alongside the environment that produced it. Vals AI’s October 13 2026 leaderboard places Claude Opus 5.5 first on SWE-bench Multimodal at 70.21 ahead of Claude Fable 5.1 at 61.25

## Why this result is conditional

**Thesis:** Benchmark leadership is meaningful only alongside the environment that produced it. Vals AI’s October 13, 2026 leaderboard places Claude Opus 5.5 first on SWE-bench Multimodal at 70.21%, ahead of Claude Fable 5.1 at 61.25%. The benchmark is not a general coding contest: **Observed fact:** it contains 480 tasks from 11 repositories, with JavaScript issues whose reports depend on screenshots or short recordings.

**Mechanism:** An agent receives the issue and image, works in a shell, and its final diff is graded using repository tests. Vals AI says every published run has no internet access because instance identifiers make the upstream pull request easy to find; agents with general access can copy the fix. **Why now:** The current leaderboard makes this constraint salient, and the page’s diagnostic reports a 21–35 percentage-point drop when network access was removed for three models. The result therefore reflects performance under a specific, deliberately constrained workflow.

**Evidence boundary:** These are leaderboard results reported by Vals AI, with each model run once; they do not establish comparative performance across all coding work or repeated-run variability. **Implication:** Teams evaluating coding agents should match benchmark conditions to their own access controls and task inputs before treating rank as a deployment forecast. **Watch condition:** Watch for repeated runs and disclosed uncertainty on this task set, plus comparable results under explicitly stated network-access conditions.

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: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- 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)