Superbash
SearchUser Hub

AI model benchmarks

Our practical model tiers. Open a model for detailed scores, comparisons, and visual runs.

S

GPT-6 AstraOpenAIClaude Fable 5.1AnthropicGrok 4.6Xai

A

Kimi K3Moonshot AIGPT-5.6 SolOpenAIDeepSeek V4 ProDeepSeekGPT-5.6 TerraOpenAIGLM 5.3Z.aiGLM 5.3 FlashZ.aiQwen3.8-MaxAlibaba Qwen

B

Gemini 3.7 FlashGoogleClaude Fable 5AnthropicDeepSeek V4 FlashDeepSeekClaude Opus 5AnthropicGPT-5.5OpenAIMuse Spark 1.2Meta

C

GPT-5.6 LunaOpenAIMiniMax M3MiniMaxGemini 3.1 Pro PreviewGoogleMiMo-V2.5-ProXiaomiClaude Sonnet 5AnthropicQwen3.7-PlusAlibaba QwenNVIDIA Nemotron 3 UltraNVIDIA

D

LongCat-2.0MeituanHy3Tencent Hy TeamStep 3.7 FlashStepFun

Additional benchmark runs

Published test sets that are not part of the current editorial tier ranking.

Composer 2.5CursorGrok 4.5XaiInklingThinking Machines LabTencent Hy4 previewTencent Hy Team
26 models across 5 tiers
248 runs across 21 tested models

Updated