LLM Reference
BrowseComp Multi-AgentactiveAgents

BrowseComp Multi-Agent: BrowseComp — Multi-Agent

Metric: Accuracy (higher is better)Introduced: 2026

BrowseComp web-browsing benchmark measured with a multi-agent workflow. Kept separate from single-agent and GPT-5.5 Pro-compute BrowseComp rows. High benchmark score alone doesn't make a model the right pick — weigh it against pricing, API availability, and release date.

Models ranked

3

tracked on this benchmark

Score band

92.2 – 86.6

best → lowest tracked

Snapshot trend

+3.70

May 28 → Jul 9 · 1 models

Leaderboard

Tracked models ranked by Accuracy (higher is better).

Compare candidates
#Model variant and provenanceScore
1
GPT-5.6 Sol
Version: BrowseComp; Sol Ultra multi-agent mode; agentic browsing; non-comparable to standard single-model rowsHarness: Not recordedEvaluator: Not recordedObserved: Jul 9, 2026Confidence: Not recordedSource

Notes: Sol Ultra multi-agent BrowseComp row; not directly comparable to standard BrowseComp rows.

92.2
2
Claude Opus 4.8
Version: BrowseComp multi-agent Dynamic WorkflowsHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource

Notes: Multi-agent BrowseComp using Dynamic Workflows; do not compare directly to GPT-5.5 Pro-compute single-agent BrowseComp.

88.5
3
Claude Sonnet 5
Version: BrowseComp multi-agent; web search, web fetch, programmatic tool calling, code execution; 10M-token limit with context compactionHarness: Not recordedEvaluator: Not recordedObserved: Jun 30, 2026Confidence: Not recordedSource
86.6

How to read this benchmark

This benchmark scores models where higher is better. Scores are useful for directional filtering and shortlisting — not for universal quality ranking. Prefer benchmarks closest to your workload, then validate the linked model pages for pricing, context window, and provider availability.

Trust this score when

  • There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
  • The model list covers the same version family you can actually deploy today.
  • Top candidates overlap with your required routing and feature requirements.

Be cautious when

  • There is only one benchmark snapshot or the dataset appears stale.
  • The benchmark metric direction is opposite of your decision objective.
  • The score difference between options is narrow and likely within implementation variance.

FAQ

What does the BrowseComp Multi-Agent benchmark measure?

BrowseComp web-browsing benchmark measured with a multi-agent workflow. Kept separate from single-agent and GPT-5.5 Pro-compute BrowseComp rows. On this page it lists 3 tracked model variants where higher is better.

Is a higher BrowseComp — Multi-Agent score always better?

For this benchmark, higher is better. A high score helps you shortlist, but confirm pricing, context window, and provider availability on each model page before committing — the top scorer is not always the right pick for your workload or budget.

How current is this BrowseComp — Multi-Agent data?

This benchmark was last reviewed on Jun 17, 2026. The tracked score average moved +3.70 points across the last 3 snapshots.

Related benchmarks

Last reviewed: Jun 17, 2026

Resources