Skip to main content

MMSearch-Plus

A harder MMSearch variant for multimodal retrieval and grounded tool-use workflows.

How BenchLM shows MMSearch-Plus right now

BenchLM is tracking MMSearch-Plus 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 MMSearch-Plus — April 10, 2026

BenchLM mirrors the published tracked score view for MMSearch-Plus. GLM-5V-Turbo leads the public snapshot at 30.0% , followed by Claude Opus 4.6 (25.6%) and Kimi K2.5 (25.6%). BenchLM does not use these results to rank models overall.

3 modelsMultimodal & GroundedCurrentDisplay onlyUpdated April 10, 2026

The published MMSearch-Plus snapshot is tightly clustered at the top: GLM-5V-Turbo sits at 30.0%, while the third row is only 4.4 points behind. The broader top-10 spread is 4.4 points, so many of the published scores sit in a relatively narrow band.

3 models have been evaluated on MMSearch-Plus. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. MMSearch-Plus is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About MMSearch-Plus

Year

2026

Tasks

Hard multimodal search tasks

Format

Advanced mixed-media retrieval benchmark

Difficulty

Advanced multimodal search

BenchLM tracks MMSearch-Plus as a display-only extension of multimodal search capability.

BenchLM freshness & provenance

Version

MMSearch-Plus 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
30.0%
2
Claude Opus 4.6claude-opus-4-6
25.6%
3
Kimi K2.5kimi-k2-5
25.6%

FAQ

What does MMSearch-Plus measure?

A harder MMSearch variant for multimodal retrieval and grounded tool-use workflows.

Which model leads the published MMSearch-Plus snapshot?

GLM-5V-Turbo currently leads the published MMSearch-Plus snapshot with a tracked score of 30.0%. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on MMSearch-Plus?

3 AI models are included in BenchLM's mirrored MMSearch-Plus snapshot, based on the public leaderboard captured on April 10, 2026.

Last updated: April 10, 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.