Skip to content

Benchmark

MathVista-Mini

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models measured
23
Scores recorded
27
Sources
2
IQ weight
3.24

Score distribution

81.1%
Mean
85.5%
Median
9.5%
Std dev
68.2%
10th percentile
87.8%
90th percentile
50%
Min
50%90.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 3.24 for chat models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.3%
2Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.1%
3Kimi K2.5setting not named by the source· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.1%
4Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.8%
5Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.4%
6Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.4%
7Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.4%
8Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.4%
9Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.4%
10Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.2%
11Qwen3.5 Omni PlusQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.1%
12Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.85.9%
13Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.85.8%
14Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.5%
15Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.84.9%
16Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.83.8%
17Qwen3.5 Omni FlashQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.9%
18qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.81.9%
19Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.81.4%
20qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.80.1%
21Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.77.2%
22Qwen2.5 VL 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.8%
23Qwen2-VL-72B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.5%
24Qwen2.5-VL 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.2%
25Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.6%
26Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.9%
27Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.