Benchmark
Dense200
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs, LLM Stats data.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 2
- IQ weight
- No weight published
Score distribution
- 56.7%
- Mean
- 42%
- Median
- 21.5%
- Std dev
- 41%
- 10th percentile
- 87%
- 90th percentile
- 41%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3.8 MaxQwen3.8-Max release vision/video table · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 87% |
| 2 | Mistral Large 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42% |
| 3 | GPT-6 AstraMistral-reported comparison· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 41% |
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