Reasoning on 111 puzzles Polish
87Scoregemini-3-pro-preview
Evaluation Results
| Method | Links | |
|---|---|---|
| gemini-3-pro-preview2026.03 | 87 | |
| o32026.03 | 87 | |
| gemini-2.5-pro2026.03 | 84 | |
| grok-42026.03 | 83 | |
| o4-mini2026.03 | 79 | |
| deepseek-R12026.03 | 78 | |
| o12026.03 | 78 | |
| seed-ossParameters=36b2026.03 | 75 | |
| k2-thinkParameters=30b2026.03 | 71 | |
| qwqParameters=32b2026.03 | 70 | |
| qwen3Parameters=8b2026.03 | 68 | |
| phi4-reasoningParameters=14b2026.03 | 68 | |
| magistral-smallParameters=24b2026.03 | 65 | |
| bielik-rParameters=11b2026.03 | 56 | |
| mistral-small3.1Parameters=24b2026.03 | 45 | |
| bielik-v3Parameters=11b2026.03 | 45 | |
| bielik-v2.6Parameters=11b2026.03 | 45 | |
| gemma-3Parameters=12b2026.03 | 44 | |
| phi4Parameters=14b2026.03 | 44 | |
| gemma-3Parameters=27b2026.03 | 42 | |
| qwen2.5Parameters=14b2026.03 | 39 | |
| bielik-v2.5Parameters=11b2026.03 | 29 | |
| bielik-v2.3Parameters=11b2026.03 | 29 |