Text Arena: LLM Rankings & AI Model Benchmarks

Text Arena🏆Overall

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Oct 15, 2026

8,834,211 votes

416 models

	Rank Spread
21	1133	GPT-5.6 Sol (xHigh) OpenAI · Proprietary	1485±4	40,442	$4 / $20	N/A
22	944	GPT-6.1 Sol (Max) OpenAI · Proprietary	1484±8	6,320	$2 / $10	1.1M
26	1542	GPT-5.5 (High) OpenAI · Proprietary	1481±4	69,401	$5 / $30	1.1M
30	1750	GPT-6 Astra (Max) OpenAI · Proprietary	1477±6	12,163	N/A	N/A
31	2247	GPT-5.5 OpenAI · Proprietary	1477±4	70,985	$5 / $30	1.1M
34	2248	GPT-5.2 Chat (20260210) OpenAI · Proprietary	1476±4	35,999	$1.75 / $14	128K
35	2249	GPT-5.4 (High) OpenAI · Proprietary	1475±4	64,776	$2.50 / $15	1.1M
43	2358	GPT-5.5 Instant OpenAI · Proprietary	1473±5	27,158	$5 / $30	1.1M
51	3562	GPT-5.6 Terra (xHigh) OpenAI · Proprietary	1466±4	43,271	$2 / $12	N/A
55	4265	GPT-5.4 OpenAI · Proprietary	1465±4	67,870	$2.50 / $15	1.1M
61	4882	GPT-6 Sol (Max) OpenAI · Proprietary	1459±6	12,466	$2 / $10	1.1M
68	5783	GPT-5.1 (High) OpenAI · Proprietary	1456±4	41,651	$0.63 / $5	400K
75	5988	GPT-5.6 Luna (xHigh) OpenAI · Proprietary	1453±4	41,109	$0.20 / $1.20	N/A
78	6292	GPT-5.3 Chat OpenAI · Proprietary	1450±4	34,345	$1.75 / $14	111.6K
85	7298	GPT-5.4 mini (High) OpenAI · Proprietary	1447±4	63,449	$0.75 / $4.50	400K
88	72107	GPT-4.5 Preview (2025-02-27) OpenAI · Proprietary	1445±6	14,547	$75 / $150	128K
91	75109	GPT-6 Luna (Max) OpenAI · Proprietary	1443±5	49,617	$0.10 / $0.50	1.1M
92	79104	ChatGPT-4o Latest (20250326) OpenAI · Proprietary	1443±3	81,914	$5 / $15	128K
99	86115	GPT-5.1 OpenAI · Proprietary	1439±4	44,434	$0.63 / $5	400K
102	87116	GPT-5.2 (High) OpenAI · Proprietary	1437±4	49,655	$0.88 / $7	400K
105	91120	GPT-5.2 OpenAI · Proprietary	1435±3	83,855	$0.88 / $7	400K
106	89123	GPT-5 (High) OpenAI · Proprietary	1435±5	31,722	$0.63 / $5	400K
112	97126	o3 (2025-04-16) OpenAI · Proprietary	1432±4	58,908	$2 / $8	200K
118	105140	GPT-5 Chat OpenAI · Proprietary	1426±4	31,188	$5 / $30	N/A
142	126153	GPT-4.1 (2025-04-14) OpenAI · Proprietary	1415±4	50,312	$2 / $8	1M
158	147171	o1 (2024-12-17) OpenAI · Proprietary	1402±4	27,807	$15 / $60	200K
161	151171	GPT-5.4 nano (High) OpenAI · Proprietary	1401±4	62,396	$0.20 / $1.25	400K
174	162189	o4-mini (2025-04-16) OpenAI · Proprietary	1391±4	44,855	$1.10 / $4.40	200K
177	162189	GPT-5 mini (High) OpenAI · Proprietary	1390±5	26,804	$0.13 / $1	400K
178	164189	o1-preview OpenAI · Proprietary	1389±5	31,122	$15 / $60	N/A
187	172193	GPT-4.1 mini (2025-04-14) OpenAI · Proprietary	1383±4	38,709	$0.40 / $1.60	1M
205	195214	o3-mini (High) OpenAI · Proprietary	1364±5	18,589	$1.10 / $4.40	200K
215	206234	gpt-oss-120b OpenAI · Apache 2.0	1352±4	30,206	$0.15 / $0.60	131.1K
220	210236	o3-mini OpenAI · Proprietary	1348±4	56,741	$0.55 / $2.20	200K
225	212237	GPT-4o (2024-05-13) OpenAI · Proprietary	1346±3	112,881	$5 / $15	128K
236	217253	GPT-5 nano (High) OpenAI · Proprietary	1338±7	8,132	$0.03 / $0.20	400K
237	222250	o1-mini OpenAI · Proprietary	1337±4	51,981	$1.10 / $4.40	N/A
240	223252	GPT-4o (2024-08-06) OpenAI · Proprietary	1336±4	45,499	$2.50 / $10	128K
253	245269	GPT-4 Turbo (2024-04-09) OpenAI · Proprietary	1325±4	98,114	$10 / $30	128K
258	242275	GPT-4.1 nano (2025-04-14) OpenAI · Proprietary	1322±8	6,103	$0.10 / $0.40	1M
265	251277	GPT-4o mini (2024-07-18) OpenAI · Proprietary	1318±4	68,705	$0.15 / $0.60	128K
267	246283	gpt-oss-20b OpenAI · Apache 2.0	1317±6	10,419	$0.02 / $0.11	131.1K
272	254284	GPT-4 Turbo Preview (0125) OpenAI · Proprietary	1313±4	93,439	$10 / $30	128K
273	254284	GPT-4 Turbo Preview (1106) OpenAI · Proprietary	1313±4	100,105	$10 / $30	128K
296	286303	GPT-4 (0314) OpenAI · Proprietary	1288±5	54,173	$30 / $60	8.2K
307	296311	GPT-4 (0613) OpenAI · Proprietary	1276±4	88,723	$30 / $60	8.2K
335	326341	GPT-3.5 Turbo (0125) OpenAI · Proprietary	1226±5	66,207	$0.50 / $1.50	16.4K
345	339353	GPT-3.5 Turbo (1106) OpenAI · Proprietary	1204±9	16,619	$1 / $2	16.4K

Text Arena🏆Overall

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Default Leaderboard Plots

Fraction of Model A Wins in A vs. B Battles (Ties Excluded)

Average Win Rate Against Each Opponent (Ties Excluded)

Battle Count for Each Pair of Models (Ties Excluded)

Confidence Intervals on Model Strength (via Bootstrapping)