Superbash
SearchUser Hub

AI model benchmarks

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

S

GPT-6 AstraOpenAIClaude Opus 5.5AnthropicClaude Fable 5.1Anthropic

A

Grok 4.7SpaceXAIGPT-6 SolOpenAIDeepSeek V4 ProDeepSeekDeepSeek V4.1 FlashDeepSeekGLM 5.3 FlashZ.aiKimi K3Moonshot AI

B

Gemini 3.7 FlashGoogleGPT-6 LunaOpenAIGLM 5.3Z.aiQwen3.8-MaxAlibaba QwenMuse Spark 1.2Meta

C

MiniMax 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 2.5CursorInklingThinking Machines LabTencent Hy4 previewTencent Hy Team
23 models across 5 tiers
137 current-model runs across 17 tested models

Updated