Benchmark
Sayf AthenaBench VSP accuracy
Vision benchmarks measure how well models understand images. Higher scores are better.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.82
Score distribution
- 0.294
- Mean
- 0.385
- Median
- 0.141
- Std dev
- 0.156
- 10th percentile
- 0.469
- 90th percentile
- 0.146
- Min
This benchmark has a weight of 0.82 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 | Gemma 4 31B ITathena_vsp· Sayf cybersecurity evaluations data docs | 0.469 |
| 2 | GPT 5.4athena_vsp· Sayf cybersecurity evaluations data docs | 0.447 |
| 3 | Claude Sonnet 4.6athena_vsp· Sayf cybersecurity evaluations data docs | 0.385 |
| 4 | Llama 3.3 70B Instructathena_vsp· Sayf cybersecurity evaluations data docs | 0.165 |
| 5 | GPT OSS 20bathena_vsp· Sayf cybersecurity evaluations data docs | 0.156 |
| 6 | Qwen3.6 35B A3Bathena_vsp· Sayf cybersecurity evaluations data docs | 0.146 |
Data credits: Sayf-eval. Copyright (c) 2026 Qatar Computing Research Institute (QCRI). MIT License. (licence)