AI model rankings · All models

Arena Elo Leaderboard — AI Models Ranked by Elo Rating

GPT-6 Astra holds the highest Arena Elo rating of the 34 AI models we track at 1288, ahead of Gemini 3.1 Pro (Preview) (1272). Elo comes from head-to-head human preference votes, so it rewards models people prefer in real conversations rather than exam accuracy. The list spans 6 providers. The lowest-cost option is Phi-4 ($0.09 blended per 1M tokens) and the longest context is GPT-6 Astra (1.1M).

Updated October 2026 · 34 models · 6 providers · prices per 1M tokens

Top 3 AI Models

AI Models Ranking

Show retired models34 of 34

Arena Elo Leaderboard — AI Models Ranked by Elo Rating

GPT-6 Astra OpenAI	$10	$50	1.1M	52.7	1384	1288	88.3	$20.00	0%
Gemini 3.1 Pro (Preview)Google	$2	$12	1M	29.7	1235	1272	85.6	$4.50	0%
GPT-6 Sol OpenAI	$2	$10	1.1M	47.6	1300	1266	84.6	$4.00	0%
Gemini 2.5 Pro Google	$1.25	$10	1M	16.1	1156	1255	82.8	$3.44	-13%
GPT-5.2 Pro OpenAI	$21	$168	400K	—	—	1255	82.8	$57.75	0%
GPT-5.6 Sol OpenAI	$2	$10	1.1M	47	1320	1255	82.8	$4.00	33%
Claude Sonnet 4 Anthropic	$3	$15	200K	16.6	1145	1250	81.9	$6.00	0%
Gemini 3.8 Flash Google	$0.75	$3.75	1M	40.9	1309	1244	81	$1.50	0%
GPT-5.3 Codex OpenAI	$1.75	$14	400K	32.5	1148	1244	81	$4.81	0%
DeepSeek R1 DeepSeek	$0.7	$2.5	64K	13.1	—	1239	80	$1.15	3%
GPT-5.2 OpenAI	$1.75	$14	400K	30.4	—	1239	80	$4.81	0%
GPT-5.6 Terra OpenAI	$2	$12	1.1M	42.1	1245	1233	79.1	$4.50	0%
Gemini 3.7 Flash Google	$0.75	$3.75	1M	39.1	1313	1228	78.2	$1.50	0%
GPT-5.1 OpenAI	$1.25	$10	400K	24.7	—	1228	78.2	$3.44	0%
Gemini 3 Flash (Preview)Google	$0.5	$3	1M	17.9	1193	1222	77.3	$1.13	0%
Gemini 3.6 Flash Google	$0.75	$3.75	1M	34	1293	1217	76.4	$1.50	0%
DeepSeek V3 DeepSeek	$0.2574	$1.0287	164K	8.5	—	1211	75.4	$0.45	-20%
Gemini 3.5 Flash Google	$1.5	$9	1M	32.6	1269	1211	75.4	$3.38	0%
GPT-6 Luna OpenAI	$0.1	$0.5	1.1M	38.1	1277	1211	75.4	$0.20	0%
Nano Banana Pro (Gemini 3 Pro Image)Google	$2	$12	131K	—	—	1211	75.4	$4.50	0%
Gemini 2.5 Flash Google	$0.3	$2.5	1M	9.9	1063	1200	73.6	$0.85	-20%
GPT-4.1 OpenAI	$2	$8	1M	12.7	1029	1200	73.6	$3.50	-9%
GPT-5.4 mini OpenAI	$0.75	$4.5	400K	24.1	—	1200	73.6	$1.69	0%
GPT-5.6 Luna OpenAI	$0.2	$1.2	1.1M	37.3	1235	1189	71.8	$0.45	0%
Mistral Large Mistral AI	$2	$6	128K	5.8	—	1189	71.8	$3.00	-25%
Nano Banana 2 (Gemini 3.1 Flash Image)Google	$0.5	$3	131K	—	—	1189	71.8	$1.13	0%
GPT-4o OpenAI	$2.5	$10	128K	8.4	864	1178	69.9	$4.38	-26%
Gemini 3.5 Flash-Lite Google	$0.3	$2.5	1M	22.2	—	1167	68.1	$0.85	0%
GPT-4.1 mini OpenAI	$0.4	$1.6	1M	10.2	997	1167	68.1	$0.70	0%
Gemini 3.1 Flash-Lite Google	$0.25	$1.5	1M	—	—	1156	66.2	$0.56	0%
GPT-5.4 nano OpenAI	$0.2	$1.25	400K	20.7	—	1156	66.2	$0.46	0%
Gemini 2.5 Flash-Lite Google	$0.1	$0.4	1M	6.7	—	1134	62.6	$0.18	0%
GPT-4o mini OpenAI	$0.15	$0.6	128K	6.7	—	1123	60.7	$0.26	-17%
Phi-4 Microsoft	$0.07	$0.14	16K	5.9	—	1123	60.7	$0.09	-16%

GPT-6 Astra OpenAI

Input /1M: $10
Output /1M: $50
Context: 1.1M
AA Intelligence: 52.7
DesignArena Elo: 1384
Arena Elo: 1288
MMLU-Pro: 88.3
Blended: $20.00
Trend: 0%

Gemini 3.1 Pro (Preview)Google

Input /1M: $2
Output /1M: $12
Context: 1M
AA Intelligence: 29.7
DesignArena Elo: 1235
Arena Elo: 1272
MMLU-Pro: 85.6
Blended: $4.50
Trend: 0%

GPT-6 Sol OpenAI

Input /1M: $2
Output /1M: $10
Context: 1.1M
AA Intelligence: 47.6
DesignArena Elo: 1300
Arena Elo: 1266
MMLU-Pro: 84.6
Blended: $4.00
Trend: 0%

Gemini 2.5 Pro Google

Input /1M: $1.25
Output /1M: $10
Context: 1M
AA Intelligence: 16.1
DesignArena Elo: 1156
Arena Elo: 1255
MMLU-Pro: 82.8
Blended: $3.44
Trend: -13%

GPT-5.2 Pro OpenAI

Input /1M: $21
Output /1M: $168
Context: 400K
AA Intelligence: —
DesignArena Elo: —
Arena Elo: 1255
MMLU-Pro: 82.8
Blended: $57.75
Trend: 0%

GPT-5.6 Sol OpenAI

Input /1M: $2
Output /1M: $10
Context: 1.1M
AA Intelligence: 47
DesignArena Elo: 1320
Arena Elo: 1255
MMLU-Pro: 82.8
Blended: $4.00
Trend: 33%

6 of 34

Compare the leaders

GPT-6 Astra vs Gemini 3.1 Pro (Preview)GPT-6 Astra vs GPT-6 Sol Gemini 3.1 Pro (Preview) vs GPT-6 Sol

How this ranking works

Benchmark is an aggregate 0–100 quality score. Blended price assumes a 3:1 input-to-output token mix. Trend compares the latest blended price with the oldest in our 6-month history.

This page sorts by arena elo. Use the panel on the right to switch ranking or category — every combination has its own page.

Frequently asked questions

All models

Text & Reasoning

Vision

Code & SLMs

Embeddings