Models

Which AI model is best right now?

Every model from the five providers we track, ranked on independent benchmarks — not the figures labs choose to publish at launch. Next to each, the cheapest subscription that includes it.

Ranked by benchmarks

Latest result 12 Nov 2026

General and Coding are our 0–100 scores, the same ones that decide a plan's model quality in the rankings. Click a column to sort by it. A dash means too few relevant benchmarks to score fairly.

AI models ranked by independent benchmarks
#	Model
1	Claude Fable 5.2 Not in a tracked subscription	92	92	173.4	56.4	—
2	Gemini 4 Carbon Not in a tracked subscription	90	92	169.8	58.3	—
3	Claude Opus 5.5 In Claude Pro · $20/mo and 2 more	88	88	168.5	59.1	—
4	GPT-6 Astra In ChatGPT Pro · $100/mo and 2 more	83	81	169	56.9	76.9
5	GPT-6.1 Sol In ChatGPT Plus · $20/mo and 2 more	80	78	168.5	52.5	—
6	Claude Fable 5.1 Not in a tracked subscription	79	78	167	49.2	81.6
7	Gemini 4 Argon Not in a tracked subscription	76	73	166.5	—	—
8	Claude Opus 5 In Claude Pro · $20/mo and 2 more	75	74	164.7	49.7	77
9	Claude Fable 5 Not in a tracked subscription	73	71	164.1	—	—
10	GPT-5.5 Pro Not in a tracked subscription	73	—	162.7	—	—
11	Claude Sonnet 5.5 In Claude Pro · $20/mo and 2 more	73	73	166.6	41.5	—
12	GPT-5.4 Pro Not in a tracked subscription	67	—	160.2	—	—
13	Claude Opus 4.8 Not in a tracked subscription	67	—	159.9	—	—
14	GPT-6.1 Terra Not in a tracked subscription	65	65	167.7	30.5	—
15	GPT-6 Sol In ChatGPT Plus · $20/mo and 4 more	64	64	163.8	34.2	—
16	GPT-5.6 Sol Not in a tracked subscription	63	64	163	33.5	69.7
17	GPT-5.5 Not in a tracked subscription	62	61	160.1	38.4	74.9
18	GPT-5.4 Not in a tracked subscription	62	—	157.9	—	—
19	Grok 4.6 In SuperGrok · $30/mo and 2 more	62	62	157.8	—	—
20	Gemini 3.8 Flash In Google AI Pro · $19.99/mo and 4 more	61	60	158.8	—	—
21	GPT-5.2 Pro Not in a tracked subscription	61	—	157.3	—	—
22	Gemini 3.7 Flash In Google AI Pro · $19.99/mo and 2 more	60	59	158.4	—	—
23	Claude Haiku 5.5 Not in a tracked subscription	60	60	160.4	34.6	—
24	Grok 4.7 In Perplexity Pro · $20/mo and 1 more	60	60	156.2	—	—
25	GPT-5.6 Terra Not in a tracked subscription	57	58	160.7	30.1	64.7
26	Claude Sonnet 5 In Claude Pro · $20/mo and 4 more	57	55	156.9	38.2	71.5
27	GPT-5.2 Not in a tracked subscription	54	—	154.5	—	—
28	Claude Opus 4.7 Not in a tracked subscription	54	54	157.4	30.9	—
29	GPT-5.3-Codex Not in a tracked subscription	53	—	157.1	—	—
30	Grok 4.5 Not in a tracked subscription	52	50	155	—	—
31	Gemini 3.5 Flash Not in a tracked subscription	52	50	155.3	32.6	70.1
32	GPT-5.6 Luna Not in a tracked subscription	51	53	156.7	23.8	71.4
33	Claude Opus 4.6 Not in a tracked subscription	50	50	156.3	26.4	—
34	Grok 4.20 Not in a tracked subscription	50	—	152.3	—	—
35	Gemini 3.6 Flash In Google AI Plus · $4.99/mo	48	43	155.2	—	—
36	GPT-6 Luna Not in a tracked subscription	47	47	156.4	23.5	—
37	GPT-5 Pro Not in a tracked subscription	47	—	151.2	—	—
38	Claude Opus 4.5 Not in a tracked subscription	47	47	151.9	29.1	—
39	GPT-5.1 Not in a tracked subscription	47	—	150.9	—	—
40	GPT-5 Not in a tracked subscription	44	—	150	—	—
41	Claude Sonnet 4.6 Not in a tracked subscription	44	44	152.9	24.7	—
42	Gemini 3 Flash Preview Not in a tracked subscription	44	—	152.3	—	—
43	Gemini 3.1 Pro Preview In Google AI Pro · $19.99/mo and 3 more	43	31	156.2	—	—
44	Claude Sonnet 4.5 Not in a tracked subscription	39	—	147.6	—	—
45	o3 Pro Not in a tracked subscription	39	—	147.5	—	—
46	GPT-5.2-Codex Not in a tracked subscription	38	—	—	28.5	—
47	GPT-5.4 Mini Not in a tracked subscription	37	37	149.3	19.7	—
48	GPT-5.4 Nano Not in a tracked subscription	36	—	146.4	—	—
49	o3 Not in a tracked subscription	34	34	147.1	20.2	—
50	Claude Opus 4.1 Not in a tracked subscription	33	—	144.8	—	—
51	GPT-5.1-Codex Not in a tracked subscription	32	—	—	23.7	—
52	Gemini 3.5 Flash Lite Not in a tracked subscription	30	33	145.6	11.7	49.3
53	Gemma 4 31B Not in a tracked subscription	29	—	144.3	—	—
54	Claude Haiku 4.5 Not in a tracked subscription	29	—	142.8	—	—
55	Gemini 3.1 Flash Lite Not in a tracked subscription	28	—	145	—	—
56	GPT-5 Mini Not in a tracked subscription	28	25	146.1	16.8	15.6
57	Gemini 2.5 Pro In Google AI Pro · $19.99/mo and 2 more	24	23	—	16.1	33.3
58	gpt-oss-120b Not in a tracked subscription	23	—	140.2	—	—
59	Gemini 2.5 Pro Preview 06-05 Not in a tracked subscription	22	—	—	14.5	—
60	Gemini 2.5 Flash Not in a tracked subscription	20	—	—	13.1	—
61	GPT-4.1 Not in a tracked subscription	17	17	136.2	12.7	—
62	GPT-5 Nano Not in a tracked subscription	16	16	139.1	7.1	—
63	gpt-oss-20b Not in a tracked subscription	14	16	135	10	20.7
64	Gemini 2.5 Flash Lite Not in a tracked subscription	10	—	—	6.7	—
65	GPT-4.1 Mini Not in a tracked subscription	9	—	134.2	—	—
66	GPT-4.1 Nano Not in a tracked subscription	0	—	126.8	—	—
67	GPT-4o-mini Not in a tracked subscription	0	—	123.9	—	—

Not enough benchmarks yet

Measured on one or two narrow benchmarks so far — usually a new release that Epoch AI and Artificial Analysis have not finished testing. Listed, not ranked, until they have.

GPT-5.1-Codex-Mini
Grok 4.3

How the scores work

Each benchmark is placed on a fixed 0–100 scale, then combined by how much it says about general or coding ability. A model is only scored on its own results; one measured on too little is not ranked. Where a model was tested at several effort settings, its best counts. The full method is on the methodology page.

Results from Epoch AI (Epoch Capabilities Index, DeepSWE, FrontierCode, CursorBench, WebDev Arena; data © Epoch AI, CC BY 4.0) and Artificial Analysis (Intelligence and Coding indexes), refreshed nightly.