Benchmark
VideoGameBench
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- 0.62
Score distribution
- 0.114%
- Mean
- 0%
- Median
- 0.186%
- Std dev
- 0%
- 10th percentile
- 0.48%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 0.62 for chat models, measured over 5 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 | Gemini 2.5 Pro Preview 03-25full, VG-Agent· VideoGameBench docs | 0.48% |
| 2 | GPT 4ofull, VG-Agent· VideoGameBench docs | 0.09% |
| 3 | Claude Sonnet 3.7full, VG-Agent· VideoGameBench docs | 0% |
| 4 | Gemini 2.0 Flashfull, VG-Agent· VideoGameBench docs | 0% |
| 5 | Llama 4 Maverickfull, VG-Agent· VideoGameBench docs | 0% |