AI Leaderboard
42 models benchmarked · updated May 31, 2026
Agentic Coding
- 🥇GPT-5.5 (xhigh)OpenAI59.1
- 🥈Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic56.7
- 🥉Gemini 3.1 Pro PreviewGoogle55.5
- 4Qwen3.7 MaxAlibaba50.1
- 5DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek47.5
- 6Muse SparkMeta47.5
- 7Grok 4.20 0309 (Reasoning)xAI42.2
- 8Mistral Medium 3.5Mistral35.4
- 9NVIDIA Nemotron 3 Super 120B A12B (Reasoning)NVIDIA31.2
Conversation
- 🥇Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic61.4
- 🥈GPT-5.5 (xhigh)OpenAI60.2
- 🥉Gemini 3.1 Pro PreviewGoogle57.2
- 4Qwen3.7 MaxAlibaba56.6
- 5Grok 4.3 (high)xAI53.2
- 6Muse SparkMeta52.2
- 7DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek51.5
- 8Mistral Medium 3.5Mistral39.2
- 9NVIDIA Nemotron 3 Super 120B A12B (Reasoning)NVIDIA36.0
Image Editing
- 🥇GPT Image 1.5 (high)OpenAI1260
- 🥈Nano Banana Pro (Gemini 3 Pro Image)Google1241
- 🥉grok-imagine-image-qualityxAI1230
- 4Wan 2.7 ProAlibaba1201
Image to Video
- 🥇grok-imagine-videoxAI1329
- 🥈Veo 3.1 Fast PreviewGoogle1282
- 🥉Wan 2.5 PreviewAlibaba1240
- 4SoraOpenAI977
Text to Image
- 🥇GPT Image 2 (high)OpenAI1338
- 🥈Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google1261
- 🥉grok-imagine-image-qualityxAI1203
- 4Qwen Image Max 2512Alibaba1161
- 5Sana Sprint 1.6BNVIDIA934
- 6Janus ProDeepSeek714
Text to Speech
- 🥇Gemini 3.1 Flash TTSGoogle1214
- 🥈xAI Text to SpeechxAI1194
- 🥉Fun-Realtime-TTS-PreviewAlibaba1193
- 4TTS-1 HDOpenAI1095
- 5Voxtral TTSMistral1067
- 6Magpie-Multilingual 357M (Feb 2026)NVIDIA1056
Text to Video
- 🥇grok-imagine-videoxAI1234
- 🥈Veo 3.1 PreviewGoogle1225
- 🥉Wan 2.6Alibaba1191
- 4Sora 2 ProOpenAI1188
Lamalo orchestrates all of this for you
Why pick one when you can have the best of every AI, for every task?
Try Lamalo