All results and scores are simulated.
OpenRouter catalog
Find a model
Suggestions come from a snapshot of the public models endpoint, cached 2026-10-11. Choosing a model builds a simulated report card against the current question set.
Roster on the leaderboard
- Claude Opus 5.5anthropic/claude-opus-5.5
- Claude Sonnet 5.5anthropic/claude-sonnet-5.5
- Claude Haiku 5.5anthropic/claude-haiku-5.5
- GPT-6 Astraopenai/gpt-6-astra
- GPT-6.1 Solopenai/gpt-6.1-sol
- GPT-6 Lunaopenai/gpt-6-luna
- Gemini 3.1 Progoogle/gemini-3.1-pro-preview
- Gemini 3.8 Flashgoogle/gemini-3.8-flash
- Grok 4.7x-ai/grok-4.7
- Grok 4.3x-ai/grok-4.3
- Mistral Large 4mistralai/mistral-large-4-0
- Mistral Medium 3.5mistralai/mistral-medium-3-5
- DeepSeek V4 Prodeepseek/deepseek-v4-pro
- DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash
- Qwen 3.8 Maxqwen/qwen3.8-max-0902
- Qwen 3.7 Plusqwen/qwen3.7-plus
- Kimi K3moonshotai/kimi-k3
- GLM-5.3z-ai/glm-5.3
- Llama 4 Maverickmeta-llama/llama-4-maverick
- gpt-oss-120bopenai/gpt-oss-120b