Benchmark
ChartQAPro
Vision benchmarks measure how well models understand images. Scores are percentages. Higher is better.
- Models measured
- 6
- Scores recorded
- 8
- Sources
- 2
- IQ weight
- 2.10
Score distribution
- 68.7%
- Mean
- 69.8%
- Median
- 2.9%
- Std dev
- 65.2%
- 10th percentile
- 70.9%
- 90th percentile
- 63.1%
- Min
This benchmark has a weight of 2.10 for chat models, measured over 6 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 | Claude Opus 4.8Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 72.3% |
| 2 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.9% |
| 3 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.9% |
| 4 | Claude Opus 4.7Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 69.8% |
| 5 | Claude Opus 4.8Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 69.4% |
| 6 | Claude Opus 4.7Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.6% |
| 7 | Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 65.2% |
| 8 | Mistral Large 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.1% |
Data credits: 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. · Data by LLM Stats