Skip to main content

BrowseComp-VL

A vision-language browsing benchmark for multimodal web research and tool-use workflows.

How BenchLM shows BrowseComp-VL right now

BenchLM is tracking BrowseComp-VL in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.

These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.

3 tracked modelsLocal tracked rowsAwaiting exact-source attachmentsDisplay only

Tracked score on BrowseComp-VL — April 16, 2026

BenchLM mirrors the published tracked score view for BrowseComp-VL. GLM-5V-Turbo leads the public snapshot at 51.9% , followed by Kimi K2.5 (42.9%) and Claude Opus 4.6 (35.9%). BenchLM does not use these results to rank models overall.

3 modelsAgenticCurrentDisplay onlyUpdated April 16, 2026

The published BrowseComp-VL snapshot is tightly clustered at the top: GLM-5V-Turbo sits at 51.9%, while the third row is only 16.0 points behind. The broader top-10 spread is 16.0 points, so the benchmark still separates strong models even when the leaders cluster.

3 models have been evaluated on BrowseComp-VL. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. BrowseComp-VL is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About BrowseComp-VL

Year

2026

Tasks

Multimodal browsing tasks

Format

Vision-language web research evaluation

Difficulty

Multimodal browser-agent

BenchLM stores BrowseComp-VL as a display-only provider-table reference while keeping BrowseComp as the weighted core browsing benchmark.

BenchLM freshness & provenance

Version

BrowseComp-VL 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Tracked score table (3 models)

1
GLM-5V-Turboglm-5v-turbo
51.9%
2
Kimi K2.5kimi-k2-5
42.9%
3
Claude Opus 4.6claude-opus-4-6
35.9%

FAQ

What does BrowseComp-VL measure?

A vision-language browsing benchmark for multimodal web research and tool-use workflows.

Which model leads the published BrowseComp-VL snapshot?

GLM-5V-Turbo currently leads the published BrowseComp-VL snapshot with a tracked score of 51.9%. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on BrowseComp-VL?

3 AI models are included in BenchLM's mirrored BrowseComp-VL snapshot, based on the public leaderboard captured on April 16, 2026.

Last updated: April 16, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.