Real-time AI Model Leaderboard

Compare 528+ AI models across intelligence, coding, reasoning, speed, and pricing. Data updated hourly from Artificial Analysis.

Benchmarks

Intelligence

Rank	Model	Score
1	Claude Opus 4.8	61.4
2	GPT-5.5	60.2
3	Claude Opus 4.7	57.3
4	Gemini 3.1 Pro	57.2
5	GPT-5.4	56.8
6	Qwen3.7 Max	56.6
7	Gemini 3.5 Flash	55.3
8	Kimi K2.6	53.9
9	MiMo-V2.5-Pro	53.8
10	GPT-5.3 Codex	53.6

Coding

Rank	Model	Score
1	GPT-5.5	59.1
2	GPT-5.4	57.2
3	Claude Opus 4.8	56.7
4	Gemini 3.1 Pro	55.5
5	GPT-5.3 Codex	53.1
6	Claude Opus 4.7	53.1
7	Claude Sonnet 4.6	50.9
8	Qwen3.7 Max	50.1
9	GPT-5.2	48.7
10	Claude Opus 4.6	48.1

Reasoning

Rank	Model	Score
1	GPT-5.2	99.0
2	GPT-5 Codex	98.7
3	Gemini 3 Flash	97.0
4	DeepSeek V3.2 Speciale	96.7
5	MiMo-V2-Flash	96.3
6	GPT-5.1 Codex	95.7
7	Gemini 3 Pro	95.7
8	GLM-4.7	95.0
9	KAT-Coder-Pro V1	94.7
10	Kimi K2 Thinking	94.7

Text to Image

Rank	Model	Score
1	GPT Image 2	1338
2	GPT Image 1.5	1267
3	Seedream 5.0	1250
4	Imagen 4	1235
5	FLUX.2	1220
6	Recraft V4.1	1195
7	Ideogram 3.0	1180
8	DALL-E 3	1150
9	Stable Diffusion 3.5	1120
10	Midjourney v6.1	1100

Image to Video

Rank	Model	Score
1	HappyHorse-1.0	1356
2	Dreamina Seedance 2.0	1215
3	Kling 3.0	1200
4	Veo 3.1	1185
5	Sora 2 Pro	1170
6	Wan 2.6	1145
7	PixVerse V6	1130
8	Vidu Q3	1110
9	Hailuo 2.3	1095
10	LTX-2.3	1080

Speed

Rank	Model	Score
1	Mercury 2	963 t/s
2	Granite 3.3 8B	446 t/s
3	gpt-oss-120b	424 t/s
4	Step 3.7 Flash	408 t/s
5	Granite 4.0 H Small	384 t/s
6	Nova Micro	342 t/s
7	Qwen3.5 2B	316 t/s
8	Gemini 3.1 Flash-Lite	311 t/s
9	Nemotron 3 Nano Omni 30B A3B Reasoning	299 t/s
10	Llama 3.1 Nemotron Instruct 70B	293 t/s

Cost

Rank	Model	Score
1	Qwen3.5 0.8B	$0.02
2	Gemma 3n E4B Instruct	$0.03
3	Qwen3.5 2B	$0.04
4	Sarvam 30B	$0.05
5	Llama 3.2 Instruct 1B	$0.05
6	Gemma 3 4B Instruct	$0.05
7	LFM2 24B A2B	$0.05
8	Qwen3.5 4B	$0.06
9	Nova Micro	$0.06
10	Granite 4.1 8B	$0.06