← All evals archived
Grab bag
A handful of small, unrelated tests — quick sanity checks on facts and instruction following.
| Model | Pass rate | Tests | Avg tokens |
|---|---|---|---|
| claude-3-7-sonnet-20250219 | 7 | – | |
| gemini-2.5-pro-preview-03-25 | 7 | – | |
| claude-3-opus-20240229 | 7 | – | |
| claude-sonnet-4-0 | 7 | – | |
| gpt-4o-mini | 7 | – | |
| gpt-5-2025-08-07 | 7 | 1.3k | |
| gpt-5-nano-2025-08-07 | 7 | 1.6k | |
| gpt-oss-120b | 14 | 659 | |
| kimi-k2-thinking (moonshotai) | 7 | 675 | |
| claude-3-5-sonnet-20241022 | 7 | – | |
| claude-opus-4-0 | 7 | – | |
| gpt-4o | 7 | – | |
| gpt-5-mini-2025-08-07 | 7 | 526 | |
| gpt-oss-20b | 7 | 776 | |
| qwen3-4b-thinking-2507 | 7 | 1.8k | |
| gemma-3-12b | 7 | – | |
| gemma-3-27b-it | 7 | – | |
| qwen3-14b | 7 | – | |
| qwen3-30b-a3b-2507 | 7 | 228 | |
| qwen3-4b-2507 | 7 | 273 |
Full results
Loading results…