Benchmark
Sayf AthenaBench CKT accuracy
Vision benchmarks measure how well models understand images. Higher scores are better.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.85
Score distribution
- 0.864
- Mean
- 0.861
- Median
- 0.043
- Std dev
- 0.822
- 10th percentile
- 0.928
- 90th percentile
- 0.811
- Min
This benchmark has a weight of 0.85 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 Sonnet 4.6ckt· Sayf cybersecurity evaluations data docs | 0.928 |
| 2 | GPT 5.4ckt· Sayf cybersecurity evaluations data docs | 0.91 |
| 3 | Gemma 4 31B ITckt· Sayf cybersecurity evaluations data docs | 0.861 |
| 4 | Qwen3.6 35B A3Bckt· Sayf cybersecurity evaluations data docs | 0.849 |
| 5 | Llama 3.3 70B Instructckt· Sayf cybersecurity evaluations data docs | 0.822 |
| 6 | GPT OSS 20bckt· Sayf cybersecurity evaluations data docs | 0.811 |
Data credits: Sayf-eval. Copyright (c) 2026 Qatar Computing Research Institute (QCRI). MIT License. (licence)