TakeTwo: benchmark results
Provider: Other.
Aggregate Rating 1162 ± 41, rank #9820 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 70.01 | Accuracy (%) (5-shot) | 24.2 |
| Open LLM Leaderboard v1 - GSM8K | 2.58 | Accuracy (%) (5-shot) | 20.4 |
| Open LLM Leaderboard v1 - HellaSwag | 62.01 | Normalized accuracy (%) (10-shot) | 15.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 37.2 | Normalized accuracy (%) (25-shot) | 14.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 36.02 | MC2 (%) (0-shot) | 3.1 |
| Open LLM Leaderboard v1 - MMLU | 23.8 | Accuracy (%) (5-shot) | 2.4 |
Interactive version: theaggregate.ai/model?slug=taketwo · How It Works · Data refreshed daily, snapshot 2026-11-08.