Benchmark
CharXiv-R
Vision benchmarks measure how well models understand images. Scores are percentages.
All vision benchmarksScores from LLM Stats data.
- Models measured
- 58
- Scores recorded
- 60
- Sources
- 1
- IQ weight
- 2.57
Score distribution
- 76.5%
- Mean
- 80.3%
- Median
- 12.9%
- Std dev
- 56.6%
- 10th percentile
- 89.9%
- 90th percentile
- 40.5%
- Min
This benchmark has a weight of 2.57 for chat models, measured over 58 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 91.3% |
| 2 | Claude Opus 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 91% |
| 3 | Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.6% |
| 4 | Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.6% |
| 5 | LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.2% |
| 6 | Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.2% |
| 7 | Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.9% |
| 8 | Gemini 3.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.4% |
| 9 | GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.4% |
| 10 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89% |
| 11 | Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 88.7% |
| 12 | Muse Spark 1.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 88.4% |
| 13 | Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 88.3% |
| 14 | Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.7% |
| 15 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.4% |
| 16 | Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.4% |
| 17 | Gemini 3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.2% |
| 18 | Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.9% |
| 19 | Inkling 2 Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.6% |
| 20 | Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 84.2% |
| 21 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83.6% |
| 22 | MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.5% |
| 23 | GPT 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.1% |
| 24 | GPT-5.5 Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.6% |
| 25 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.5% |
| 26 | Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.4% |
| 27 | GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.1% |
| 28 | MiMo V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81% |
| 29 | NVIDIA Nemotron 3.5 Super VL 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.8% |
| 30 | Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.3% |
| 31 | Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 79.5% |
| 32 | Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.8% |
| 33 | OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.6% |
| 34 | Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.4% |
| 35 | Inkling FP4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.1% |
| 36 | Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78% |
| 37 | Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.5% |
| 38 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.5% |
| 39 | Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.4% |
| 40 | Inkling Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.4% |
| 41 | Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.2% |
| 42 | Gemini 3.5 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.5% |
| 43 | Gemini 3.1 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.2% |
| 44 | o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72% |
| 45 | Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.4% |
| 46 | Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.8% |
| 47 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 66.1% |
| 48 | Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 65.2% |
| 49 | Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 62.8% |
| 50 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 62.1% |
Showing 1–50 of 60 results.
Data credits: Data by LLM Stats