Catalogue

Latest models

Model Provider Released Context Weights
Kimi K2.7 Code Moonshot AI Jun 12, 2026 open
DiffusionGemma 26B-A4B Google Jun 10, 2026 open
Claude Fable 5 Anthropic Jun 9, 2026 proprietary
U2 Unisound Jun 5, 2026 proprietary
MAI-Code-1-Flash Microsoft Jun 2, 2026 proprietary
MAI-Thinking-1 Microsoft Jun 2, 2026 proprietary

Featured leaderboards

AA-LCR

# Model Score
1 Mistral Small 4 71.2%
2 Kimi K2.5 70.0%
3 Qwen3.5-397B-A17B 68.7%
4 Qwen3.6 Plus 68.3%
5 Qwen3.5-122B-A10B 66.9%

AI2D

# Model Score
1 Claude 3.5 Sonnet 94.7%
2 Qwen3.6 Plus 94.4%
3 GPT-4o 94.2%
4 Pixtral Large 93.8%
5 Qwen3.5-122B-A10B 93.3%
# Model Score
1 GPT-5 88.0%
2 Gemini 2.5 Pro Preview 06-05 82.2%
3 o3 81.3%
4 Gemini 2.5 Pro 76.5%
5 DeepSeek-V3.2-Exp 74.5%