Benchmark
CharadesSTA
Vision benchmarks measure how well models understand images. Scores are percentages.
All vision benchmarksScores from LLM Stats data.
- Models measured
- 7
- Scores recorded
- 9
- Sources
- 1
- IQ weight
- 1.97
Score distribution
- 59.8%
- Mean
- 62.7%
- Median
- 6.2%
- Std dev
- 56%
- 10th percentile
- 63.5%
- 90th percentile
- 43.6%
- Min
This benchmark has a weight of 1.97 for chat models, measured over 7 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 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 64.8% |
| 2 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 63.5% |
| 3 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 63.5% |
| 4 | Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 62.8% |
| 5 | qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 62.7% |
| 6 | Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 61.2% |
| 7 | Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 59.9% |
| 8 | Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 56% |
| 9 | Qwen2.5-VL 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.6% |
Data credits: Data by LLM Stats