# BrowseComp (10-agent, prerelease) leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/agentic-multi-agent-browse-comp-prerelease

Multi-Agent BrowseComp — 10-agent team prerelease configuration. Every model the catalog carries a published BrowseComp (10-agent, prerelease) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | 10-agent team accuracy |
| Tasks | BrowseComp web-research tasks |
| Difficulty | Long-horizon web research |
| Published by | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |

BrowseComp accuracy from ten collaborating Opus 5 agents on a pre-release model and unreleased effort configuration.

## BrowseComp (10-agent, prerelease) ranking

1 model with a published BrowseComp (10-agent, prerelease) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | 10-agent team accuracy | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 93.6 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
