LLM Reference
BrowseComp SingleactiveAgents

BrowseComp Single: BrowseComp — Single Agent

Metric: Accuracy (higher is better)Introduced: 2025

BrowseComp web-browsing benchmark measured in a single-agent setup. Kept separate from Pro-compute and multi-agent BrowseComp variants.

Models ranked

2

tracked on this benchmark

Score band

84.4 – 84.3

best → lowest tracked

Snapshot trend

-0.10

Apr 24 → May 28 · 1 models

Leaderboard

Tracked models ranked by Accuracy (higher is better).

Compare candidates
#Model variant and provenanceScore
1
GPT-5.5 Pro
Version: BrowseComp single-agent; standard GPT-5.5 weightsHarness: Not recordedEvaluator: Not recordedObserved: Apr 24, 2026Confidence: Not recordedSource

Notes: Standard single-agent BrowseComp row; kept separate from GPT-5.5 Pro-compute BrowseComp.

84.4
2
Claude Opus 4.8
Version: BrowseComp single-agentHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource

Notes: Single-agent BrowseComp variant for direct comparison with GPT-5.5 standard single-agent row.

84.3

How to read this benchmark

This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.

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.

Related benchmarks

Last reviewed: Jun 17, 2026

Resources