Context AI model rankings

The Context track ranks 40 AI models by the usable context window in tokens. Snapshot 2026-10-14, updated weekly.

Snapshot 2026-10-14 · updated weekly

Rank	Model	Vendor	Context	GPQA	Context	Price (in / out)	Speed
1▲2	Gemini 4 ArgonClosed	Google	2M	92.1%	2M	$2.50 / $12	165
2—	Gemini 4.0Closed	Google	2M	87.9%	2M	$2.20 / $10	158
3—	Grok-4 Fast ReasoningClosed	xAI	2M	81.5%	2M	$0.80 / $3.20	210
4▲1	GPT-6.1 SolClosed	OpenAI	1M	94.9%	1M	$6 / $36	112
5▼1	GPT-6 AstraClosed	OpenAI	1M	96%	1M	$5 / $30	128
6▲1	MiniMax H3Open	MiniMax	1M	85.8%	1M	$0.60 / $2.20	121
7▲2	Gemini 3.8 FlashClosed	Google	1M	78.9%	1M	$0.15 / $0.60	342
8—	Gemini 3 ProClosed	Google	1M	80.9%	1M	$1.50 / $6	168
9—	Gemini 3.1 ProClosed	Google	1M	79.8%	1M	$1.25 / $5	172
10—	GPT-6 SolClosed	OpenAI	800K	90.2%	800K	$4 / $24	118
11—	GPT-5.6 SolClosed	OpenAI	512K	88.4%	512K	$2.80 / $16	134
12—	Kimi K3Open	Moonshot AI	512K	93.5%	512K	$0.50 / $2	98
13—	Muse Wonder FullOpen	Meta	512K	88.1%	512K	$0.90 / $3.20	88
14▲1	Qwen3.8 NextOpen	Alibaba	512K	82.9%	512K	$0.50 / $1.80	104
15—	MiniMax H3 FlashOpen	MiniMax	512K	72.6%	512K	$0.10 / $0.40	358
16—	GPT-5.6 LunaClosed	OpenAI	512K	74.2%	512K	$1.20 / $5.50	286
17—	Claude Opus 5.5Closed	Anthropic	500K	95.8%	500K	$8 / $40	88
18—	Claude Sonnet 5.5Closed	Anthropic	500K	92.8%	500K	$3 / $15	156
19NEW	Claude Haiku 5.5Closed	Anthropic	500K	83.2%	500K	$0.80 / $4	232
20—	Claude Fable 5.1Closed	Anthropic	400K	93.4%	400K	$4 / $20	142
21—	Claude Fable 5Closed	Anthropic	400K	91.9%	400K	$3.50 / $18	138
22▼1	Claude Opus 5Closed	Anthropic	400K	90.7%	400K	$6 / $30	96
23NEW	DeepSeek HarnessOpen	DeepSeek	256K	86.5%	256K	$0.35 / $1.40	105
24—	GLM-5.3Open	Zhipu AI	256K	85.2%	256K	$0.40 / $1.50	118
25—	Muse WonderOpen	Meta	256K	85.9%	256K	$0.45 / $1.60	126
26—	DeepSeek V4.5Open	DeepSeek	256K	83.7%	256K	$0.30 / $1.20	112
27▲3	GLM-5.3 FlashOpen	Zhipu AI	256K	80.4%	256K	$0.12 / $0.50	268
28—	Mistral Large 3.5Open	Mistral AI	256K	80.7%	256K	$0.80 / $2.40	132
29—	Qwen3.8 27BOpen	Alibaba	256K	76.8%	256K	$0.15 / $0.60	186
30—	MiMo-V2.6-ProOpen	Xiaomi	256K	75.4%	256K	$0.25 / $1	142
31—	Kimi K3 FlashOpen	Moonshot AI	256K	70.2%	256K	$0.14 / $0.55	296
32—	Qwen3.8 FlashOpen	Alibaba	256K	66.8%	256K	$0.06 / $0.25	412
33—	Gemma 4 27BOpen	Google	256K	67.4%	256K	$0.18 / $0.70	174
34NEW	Strata 2Open	Strata Labs	128K	62.8%	128K	$0.12 / $0.45	248
35NEW	Jev 1Open	Jev Labs	128K	59.4%	128K	$0.08 / $0.30	322
36NEW	Clef 2Open	Clef AI	128K	56.9%	128K	$0.10 / $0.35	276
37—	Mercury 2.5Open	Inception Labs	128K	48.2%	128K	$0.10 / $0.40	583
38—	Celeris-1Closed	Celeris	128K	42.6%	128K	$0.20 / $0.80	1431
39NEW	Laya 1Open	Laya Research	64K	38.4%	64K	$0.05 / $0.20	368
40NEW	Pixel CanaryClosed	Google	32K	31.2%	32K	Free / Free	210

Context FAQ

Which AI model is best for Context?

Gemini 4 Argon leads the Context track as of October 2026. The full table above ranks all 40 tracked models on this dimension, with the underlying values shown for every row.

How is the Context ranking calculated?

This track ranks models by the usable context window in tokens. Scores are re-verified weekly against public benchmark sources and API rate cards, and the snapshot date is shown on every table so you can see exactly how fresh each value is.