List your company

Reasoning on 111 puzzles Polish

87Scoregemini-3-pro-preview
26.6842.345873.66Mar 11, 2026

Evaluation results

MethodLinks
gemini-3-pro-preview2026.0387
o32026.0387
gemini-2.5-pro2026.0384
grok-42026.0383
o4-mini2026.0379
deepseek-R12026.0378
o12026.0378
seed-ossParameters=36b2026.0375
k2-thinkParameters=30b2026.0371
qwqParameters=32b2026.0370
qwen3Parameters=8b2026.0368
phi4-reasoningParameters=14b2026.0368
magistral-smallParameters=24b2026.0365
bielik-rParameters=11b2026.0356
mistral-small3.1Parameters=24b2026.0345
bielik-v3Parameters=11b2026.0345
bielik-v2.6Parameters=11b2026.0345
gemma-3Parameters=12b2026.0344
phi4Parameters=14b2026.0344
gemma-3Parameters=27b2026.0342
qwen2.5Parameters=14b2026.0339
bielik-v2.5Parameters=11b2026.0329
bielik-v2.3Parameters=11b2026.0329