Buckets:
| Model | n | mean reward | feasible | submitted | easy | medium | hard | beat naive | optimal |
|---|---|---|---|---|---|---|---|---|---|
| openai:gpt-6.1-sol | 50 | 0.888 | 100% | 100% | - | - | - | 50 | 26 |
| anthropic:claude-sonnet-5-5 | 50 | 0.782 | 98% | 98% | - | - | - | 49 | 10 |
| hf:zai-org/GLM-5.3-Flash:baseten | 50 | 0.470 | 50% | 72% | - | - | - | 25 | 9 |
| hf:Qwen/Qwen3.8-2.4T-A95B:together | 50 | 0.380 | 46% | 68% | - | - | - | 23 | 5 |
| hf:zai-org/GLM-5.3:together | 50 | 0.313 | 32% | 34% | - | - | - | 16 | 10 |
| hf:Qwen/Qwen3.8-27B:cerebras | ovhcloud | 50 | 0.211 | 26% | 32% | - | - | - | 13 |
Xet Storage Details
- Size:
- 634 Bytes
- Xet hash:
- 7d5eaff2afad7a0a50615ba582a71f7f4b5b57cfb792586cf8ae47482e875725
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.