Skip to main content

MathVision

A visual mathematics benchmark that tests whether a model can solve math problems grounded in diagrams, equations, figures, and other visual inputs.

How BenchLM shows MathVision right now

BenchLM is tracking MathVision 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.

6 tracked modelsLocal tracked rowsAwaiting exact-source attachmentsDisplay only

Tracked score on MathVision — April 16, 2026

BenchLM mirrors the published tracked score view for MathVision. Qwen3.5 397B leads the public snapshot at 88.6% , followed by Qwen3.6 Plus (88.0%) and Gemini 3 Pro (86.6%). BenchLM does not use these results to rank models overall.

6 modelsMultimodal & GroundedCurrentDisplay onlyUpdated April 16, 2026

The published MathVision snapshot is tightly clustered at the top: Qwen3.5 397B sits at 88.6%, while the third row is only 2.0 points behind. The broader top-10 spread is 14.3 points, so the benchmark still separates strong models even when the leaders cluster.

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

About MathVision

Year

2026

Tasks

Visually grounded math problems

Format

Image + math reasoning

Difficulty

Advanced multimodal mathematics

MathVision matters because text-only math ability does not guarantee strong performance when the relevant information is embedded in images, geometry diagrams, or formatted equations.

BenchLM freshness & provenance

Version

MathVision 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 (6 models)

1
Qwen3.5 397Bqwen3-5-397b
88.6%
2
Qwen3.6 Plusqwen3-6-plus
88.0%
3
Gemini 3 Progemini-3-pro
86.6%
4
Kimi K2.5kimi-k2-5
84.2%
5
GPT-5.2gpt-5-2
83.0%
6
Claude Opus 4.5claude-opus-4-5
74.3%

FAQ

What does MathVision measure?

A visual mathematics benchmark that tests whether a model can solve math problems grounded in diagrams, equations, figures, and other visual inputs.

Which model leads the published MathVision snapshot?

Qwen3.5 397B currently leads the published MathVision snapshot with a tracked score of 88.6%. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on MathVision?

6 AI models are included in BenchLM's mirrored MathVision 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.