Leaderboard
MCQ Arena rankings
0 votes·0 rated models·K=32 Elo · updates live
Free resources from Test Community Network
Practical guides to help assessment professionals understand and use AI responsibly.
Filters
| Pick | # | ||||||
|---|---|---|---|---|---|---|---|
| 1 | gpt-6-astra OpenAI | 1000 | 0 | 0 | 0 | — | |
| 2 | gpt-5.5 OpenAI | 1000 | 0 | 0 | 0 | — | |
| 3 | gpt-5 OpenAI | 1000 | 0 | 0 | 0 | — | |
| 4 | gpt-5-mini OpenAI | 1000 | 0 | 0 | 0 | — | |
| 5 | gpt-4o OpenAI | 1000 | 0 | 0 | 0 | — | |
| 6 | gpt-4o-mini OpenAI | 1000 | 0 | 0 | 0 | — | |
| 7 | gemini-2.5-pro Google | 1000 | 0 | 0 | 0 | — | |
| 8 | gemini-2.5-flash Google | 1000 | 0 | 0 | 0 | — | |
| 9 | gemini-2.5-flash-lite Google | 1000 | 0 | 0 | 0 | — | |
| 10 | claude-fable-5.1 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 11 | claude-opus-5 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 12 | claude-fable-5 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 13 | claude-opus-4.8 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 14 | claude-sonnet-5 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 15 | claude-opus-4.1 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 16 | claude-sonnet-4.5 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 17 | claude-haiku-4.5 Anthropic | 1000 | 0 | 0 | 0 | — | |
| 18 | gemini-3.8-flash Google | 1000 | 0 | 0 | 0 | — | |
| 19 | grok-4.3 xAI | 1000 | 0 | 0 | 0 | — | |
| 20 | kimi-k3 Moonshot AI | 1000 | 0 | 0 | 0 | — | |
| 21 | llama-3.3-70b Meta | 1000 | 0 | 0 | 0 | — | |
| 22 | deepseek-v3.1 DeepSeek | 1000 | 0 | 0 | 0 | — | |
| 23 | qwen-2.5-72b Qwen | 1000 | 0 | 0 | 0 | — | |
| 24 | mistral-small-3.2 Mistral | 1000 | 0 | 0 | 0 | — | |
| 25 | inkling Thinking Machines | 1000 | 0 | 0 | 0 | — |
Cost estimated from token usage × published list prices. Cached / discount rates will differ.