Benchmark profile

MathVision

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

Data verified July 23, 2026

Benchmark score on MathVision — July 23, 2026

BenchLM mirrors the published score view for MathVision. Kimi K3 leads the public snapshot at 94.3% , followed by Qwen3.7 Plus (90.3%) and Qwen3.5 397B (88.6%). BenchLM does not use these results to rank models overall.

1Closed

Kimi K3

Moonshot AI

kimi-3

94.3%

Overall 80.96Context 1.05M

2Closed

Qwen3.7 Plus

Alibaba

qwen3-7-plus

90.3%

Overall 67.22Context 1M

3Open

Qwen3.5 397B

Alibaba

qwen3-5-397b

88.6%

Overall 57.01Context 128K

12 modelsMultimodal & GroundedCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (12 models)

Score

Kimi K3Moonshot AI · Closed

94.3%

Qwen3.7 PlusAlibaba · Closed

90.3%

Qwen3.5 397BAlibaba · Open weight

88.6%

Qwen3.6 PlusAlibaba · Closed

88.0%

Kimi K2.6Moonshot AI · Open weight

87.4%

Gemini 3 ProGoogle · Closed

86.6%

Qwen3.5-122B-A10BAlibaba · Open weight

86.2%

Qwen3.5-27BAlibaba · Open weight

86.0%

Qwen3.5-35B-A3BAlibaba · Open weight

83.9%

GPT-5.2OpenAI · Closed

83.0%

Gemma 4 12BGoogle · Open weight

79.7%

Claude Opus 4.5Anthropic · Closed

74.3%

The published MathVision snapshot places Kimi K3 first at 94.3%. The third row is 5.7 points behind. The broader top-10 range is 11.3 points, so the table still separates the published systems.

12 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.

Qwen3.6 launch benchmarks

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.

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 scores highest on MathVision?

Kimi K3 by Moonshot AI currently leads with a score of 94.3% on MathVision.

How many models are evaluated on MathVision?

12 AI models have been evaluated on MathVision on BenchLM.

Compare Top Models on MathVision

Kimi K3 vs Qwen3.7 Plus Qwen3.7 Plus vs Qwen3.5 397B Qwen3.5 397B vs Qwen3.6 Plus Qwen3.6 Plus vs Kimi K2.6

Last updated: July 23, 2026 · BenchLM version MathVision 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.