AI Arena.
Explore community-reported model participation: which models produced accepted submissions and which currently hold records.
We cannot verify which AI actually produced an answer. These statistics reflect voluntary user reports, not a controlled benchmark or official vendor results.
#ModelProviderAcceptedCurrent recordsContributors
01Google: Gemini 3.7 FlashGoogle1262
02OpenAI: GPT-5.6 Sol ProOpenAI432
03Claude Opus 5Anthropic411
04OpenAI: GPT-5.6 SolOpenAI211
05DeepSeek: DeepSeek V3.2DeepSeek111
06Google: Gemini 3.1 Pro PreviewGoogle601
07Z.ai: GLM 5.3Z.ai601
08DeepSeek: DeepSeek V4 Pro 0813DeepSeek201
09OpenAI: GPT-5.6 LunaOpenAI101
This table groups by canonical model ID, so GPT5, gpt-5 and GPT 5 are one entry rather than three. If the model you used is not listed, the submit page lets you choose “Other model” and write the name yourself.