Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

MMAnswerBench

We mirror this table; we do not rank on it.

Data verified 36 confirmed releases in the last 30 daysFollow model changes

A multimodal mathematical reasoning benchmark that tests whether models can answer visually grounded math questions correctly.

Benchmark score on MMAnswerBench — September 18, 2026

We mirror the published score view for MMAnswerBench. GLM-5.2 leads the public snapshot at 91.0%, followed by Kimi K2.6 (86.0%) and Claude Opus 4.5 (84.0%). We do not use these results to rank models overall.

1Open weights

GLM-5.2

Z.AI

91.0%
Overall 66.68Context 1M
2Open weights

Kimi K2.6

Moonshot AI

86.0%
Overall 65.5Context 256K
3Proprietary

Claude Opus 4.5

Anthropic

84.0%
Overall 58.42Context 200K

10 modelsMathCurrentDisplay onlyUpdated September 18, 2026

Benchmark score table (10 models)

Score
1
GLM-5.2Z.AI · Open weight
91.0%
2
Kimi K2.6Moonshot AI · Open weight
86.0%
3
Claude Opus 4.5Anthropic · Closed
84.0%
4
GLM-5.1Z.AI · Open weight
83.8%
5
Qwen3.6 PlusAlibaba · Closed
83.8%
6
GLM-5Z.AI · Open weight
82.5%
7
Kimi K2.5Moonshot AI · Open weight
81.8%
8
Qwen3.5 397BAlibaba · Open weight
80.9%
9
Qwen3.6-27BAlibaba · Open weight
80.8%
10
Qwen3.6-35B-A3BAlibaba · Open weight
78.9%

The published MMAnswerBench snapshot places GLM-5.2 first at 91.0%. The third row is 7.0 points behind. The broader top-10 range is 12.1 points, so the table still separates the published systems.

10 models have been evaluated on MMAnswerBench. The benchmark falls in the Math category. This category carries a 5% weight in BenchLM.ai's overall scoring system. MMAnswerBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About MMAnswerBench

Year

2026

Tasks

Multimodal math questions

Format

Visual and structured mathematical QA

Difficulty

Advanced mathematical reasoning

MMAnswerBench matters because text-only math ability does not guarantee strong performance when the relevant information is embedded in diagrams, tables, or other visual inputs. It acts as a multimodal math transfer check.

Qwen3.6 launch benchmarks

Freshness and provenance

Version

MMAnswerBench 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.

Questions

What does MMAnswerBench measure?

A multimodal mathematical reasoning benchmark that tests whether models can answer visually grounded math questions correctly.

Which model scores highest on MMAnswerBench?

GLM-5.2 by Z.AI currently leads with a score of 91.0% on MMAnswerBench.

How many models are evaluated on MMAnswerBench?

10 AI models have been evaluated on MMAnswerBench on BenchLM.

Compare top models on MMAnswerBench

GLM-5.2 vs Kimi K2.6Kimi K2.6 vs Claude Opus 4.5Claude Opus 4.5 vs GLM-5.1GLM-5.1 vs Qwen3.6 Plus
Last updated: September 18, 2026 · BenchLM version MMAnswerBench 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.