Benchmark
Sayf AthenaBench TAA accuracy
Vision benchmarks measure how well models understand images. Higher scores are better.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 1.04
Score distribution
- 0.232
- Mean
- 0.22
- Median
- 0.102
- Std dev
- 0.16
- 10th percentile
- 0.42
- 90th percentile
- 0.11
- Min
This benchmark has a weight of 1.04 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 4.6taa· Sayf cybersecurity evaluations data docs | 0.42 |
| 2 | GPT 5.4taa· Sayf cybersecurity evaluations data docs | 0.3 |
| 3 | Gemma 4 31B ITtaa· Sayf cybersecurity evaluations data docs | 0.22 |
| 4 | Llama 3.3 70B Instructtaa· Sayf cybersecurity evaluations data docs | 0.18 |
| 5 | Qwen3.6 35B A3Btaa· Sayf cybersecurity evaluations data docs | 0.16 |
| 6 | GPT OSS 20btaa· Sayf cybersecurity evaluations data docs | 0.11 |
Data credits: Sayf-eval. Copyright (c) 2026 Qatar Computing Research Institute (QCRI). MIT License. (licence)