← All evals archived
Article tracking: Trump categories
How well do the llm categories match up with mine?
| Model | Pass rate | Tests | Avg tokens |
|---|---|---|---|
| kimi-k2-thinking (moonshotai) | 97 | 706 | |
| claude-opus-4-0 | 97 | 6 | |
| claude-sonnet-4-0 | 97 | 6 | |
| claude-sonnet-4-5 | 97 | 16 | |
| qwen3-14b | 97 | – | |
| gpt-4o | 97 | 4 | |
| gpt-4o-mini | 97 | 4 | |
| gemma-3-12b | 97 | – | |
| qwen3-30b-a3b-2507 | 97 | 4 |
Full results
Loading results…