AISOTA· State of the Art

Daily AI Decision Intelligence

Multi-source rankings blended into one score. See which model is truly State of the Art — today.

Data as of 2026-08-18Updated Aug 18, 05:01 PM

Overall Intelligence

Multi-source blend of general intelligence benchmarks into a single AISOTA score.

#	Model	Artificial Analysis	LiveBench	AISOTA Score
1SOTA	Claude Fable 5 (with fallback)2 sources	90.0	97.7	93.8
22	gpt-5.5-xhigh	—	93.2	93.2
33	Claude Opus 5 (max)2 sources	95.0	90.9	93.0
4	GPT-5.6 Sol (max)2 sources	85.0	95.5	90.3
5	smaug-agentic	—	86.4	86.4
6	Grok 4.6 (high)2 sources	80.0	79.5	79.8
7	Kimi K3 (max)2 sources	75.0	81.8	78.4
8	Qwen3.8 Max2 sources	70.0	84.1	77.0
9	gpt-5.4-xhigh	—	75.0	75.0
10	Gemini 3.7 Flash (high)2 sources	55.0	88.6	71.8

Multi-source blend of coding benchmarks into a single AISOTA score.

#	Model	Artificial Analysis Agentic	LiveBench Coding	AISOTA Score
1SOTA	smaug-agentic	—	97.7	97.7
22	Claude Opus 5 (max)2 sources	95.0	93.2	94.1
33	Qwen3.8 Max2 sources	85.0	88.6	86.8
4	claude-sonnet-5-xhigh-effort	—	86.4	86.4
5	Claude Fable 5 (with fallback)2 sources	75.0	95.5	85.3
6	GPT-5.6 Sol (max)2 sources	80.0	84.1	82.0
7	Grok 4.6 (high)2 sources	90.0	72.7	81.3
8	Kimi K3 (max)2 sources	70.0	90.9	80.5
9	muse-spark-1.1-xhigh	—	79.5	79.5
10	gpt-5.5-xhigh	—	75.0	75.0

Intelligence per dollar, based on median input + output price.

#	Model	AA Intelligence	OpenRouter Price	AISOTA Score
1SOTA	Gemini 3.7 Flash (high)2 sources	55.0	65.4	60.2
22	GPT-5.6 Luna (max)2 sources	40.0	75.3	57.6
33	Claude Opus 5 (max)2 sources	95.0	11.5	53.3
4	GPT-5.6 Sol (max)2 sources	85.0	17.3	51.1
5	Grok 4.6 (high)2 sources	80.0	20.3	50.1
6	MiniMax-M32 sources	25.0	73.2	49.1
7	Claude Fable 5 (with fallback)2 sources	90.0	5.8	47.9
8	Muse Spark 1.2 (xhigh)2 sources	65.0	25.8	45.4
9	Qwen3.8 Max2 sources	70.0	20.0	45.0
10	Kimi K3 (max)2 sources	75.0	7.8	41.4

API request volume per model over the last 7 days, sourced from OpenRouter public rankings.

#	Model	OpenRouter Usage	AISOTA Score
1SOTA	deepseek-v4-flash	889.26M	99.8
22	gemini-2-5-flash-lite	252.51M	99.5
33	gpt-5-6-luna	250.77M	99.3
4	hy3	126.05M	99.0
5	gemini-2-5-flash	118.97M	98.8
6	gpt-4o-mini	117.25M	98.6
7	gemini-3-1-flash-lite	115.47M	98.3
8	deepseek-v4-pro	112.05M	98.1
9	gpt-oss-120b	109.51M	97.9
10	text-embedding-3-small	107.23M	97.6