No results yet
This board fills as models are run and a grader scores them.
Latest runs8
| Model | Score | Cost | Time | Published | How |
|---|---|---|---|---|---|
| Palmyra-X-004 | 73.9 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
| Palmyra X V3 (72B) | 70.2 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
| Palmyra X V2 (33B) | 62.1 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
| Solar Pro | 67.9 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
| GPT-4o mini (2024-07-18) | 66.8 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
| GPT-4o (2024-08-06) | 73.8 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
| GPT-4o (2024-05-13) | 74.8 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
| GPT-4 Turbo (2024-04-09) | 71.1 | $0 | 0 ms | 2026-10-30 18:44 UTC | submitted |
Download the dataset JSONL from Bench.