MathVision
AI benchmark results and model performance
Type: percentageMath
Recorded results
52
Average score
55.87%
Score range
25% - 94.60%
Leading model
94.60% - Qwen 3.8 27B
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Qwen 3.8 27B | 14 Aug 2026 | 94.60% | With CI; without CI: 90.0 | Yes | Source | |
| Kimi K3 | 16 Jul 2026 | 94.30% | Average of three runs. | Yes | Source | |
| Seed 2.0 Pro | 14 Feb 2026 | 88.80% | Seed2 official benchmark table | MathVision | Yes | Source | |
| Qwen 3.6 Plus | 01 Apr 2026 | 88% | - | Yes | Source | |
| Seed 2.0 Lite | 14 Feb 2026 | 86.40% | Seed2 official benchmark table | MathVision | Yes | Source | |
| Qwen 3.5 122B A10B | 24 Feb 2026 | 86.20% | Highest reported variant uses fixed boxed-answer prompt. | Yes | Source | |
| Qwen 3.5 27B | 24 Feb 2026 | 86% | Highest reported variant uses fixed boxed-answer prompt. | Yes | Source | |
| Qwen 3.5 Flash | 23 Feb 2026 | 86% | inferred family alias from qwen3.5-27b (score=0.4147; benches=81) | Yes | Source | |
| Kimi K2.5 | 27 Jan 2026 | 84.20% | - | Yes | Source | |
| Qwen 3.5 35B A3B | 24 Feb 2026 | 83.90% | Highest reported variant uses fixed boxed-answer prompt. | Yes | Source | |
| Seed 2.0 Mini | 14 Feb 2026 | 78.10% | Seed2 official benchmark table | MathVision | Yes | Source | |
| Qwen 3 VL 235B A22B Thinking | - | 74.60% | - | Yes | - | |
| DiffusionGemma 26B A4B IT | 10 Jun 2026 | 70.50% | - | Yes | Source | |
| Qwen 3 VL 32B Thinking | - | 70.20% | - | Yes | - | |
| Qwen 3 VL 235B A22B Instruct | - | 66.50% | - | Yes | - | |
| Qwen 3 VL 30B A3B Thinking | - | 65.70% | - | Yes | - | |
| Qwen 3 VL 32B Instruct | - | 63.40% | - | Yes | - | |
| Qwen 3 8B | - | 62.70% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Yes | - | |
| Qwen 3 Guard Stream 8B | - | 62.70% | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Yes | - | |
| Qwen 3 VL 8B Thinking | - | 62.70% | - | Yes | - | |
| Qwen 3 VL Embedding 8B | - | 62.70% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Yes | - | |
| Qwen 3 VL Reranker 8B | - | 62.70% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Yes | - | |
| Qwen 3 VL 30B A3B Instruct | - | 60.20% | - | Yes | - | |
| Qwen 3 4B Instruct 2507 | - | 60% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Yes | - | |
| Qwen 3 4B SafeRL | - | 60% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Yes | - |
