Intelligence per dollar

Name: LLM intelligence per dollar
Creator: AI Calculator Pro
License: https://creativecommons.org/licenses/by/4.0/

The smartest model is rarely the one you should ship. This board ranks every major LLM by community Arena score and by intelligence per dollar, and flags the models on the price/quality frontier — the ones nothing else beats on both quality and cost. Pick an arena, then sort by what matters for your task.

Find the cheapest model for my task Can I downgrade & save?

Decision-ready picks

Skip the leaderboard — here’s the one model that best answers each common question (overall arena).

Best overall

Gemini 4 Argon

Google · Arena 1529

The highest-scoring model we track for this arena — the quality ceiling.

Best value

GPT OSS 20B

OpenAI · 171600 Elo per $/1M

The most Arena score per dollar — punches far above its price.

Cheapest that clears the bar

GPT OSS 120B

OpenAI · $0.017/1M blended

The lowest price among models still within 15% of the top Arena score.

Largest useful context

Llama 4 Scout

Meta · 10M tokens

The biggest context window among genuinely capable models — for long docs and codebases.

Best for coding

Claude Opus 5.5

Anthropic · Coding Arena 1810

Top of the coding Arena — the safest pick for agents and multi-file edits.

Price vs performance

Every scored model plotted by price and Arena score. The best value sits toward the top-left.

Price vs quality — lower and higher is better. Highlighted points are on the price/quality frontier (nothing we track beats them on both). Price uses a 3:1 blended $/1M on a log scale.

7 of 207 models are on the price/quality frontier (marked Best value). An Est. tag means the score is inherited from the base model (a regional/creator-prefixed hosting duplicate). Click a column to sort; click again to flip.


1	Gemini 4 ArgonBest value	1529	$4.00	382	Google
2	Claude Opus 5.5	1516	$8.00	190	Anthropic
3	Claude Opus 5.5 (Bedrock)Est.	1516	$8.80	172	AWS Bedrock
4	Claude Fable 5.1	1514	$20.00	76	Anthropic
5	Claude Fable 5.1 (Bedrock)Est.	1514	$22.00	69	AWS Bedrock
6	Claude Opus 5	1504	$10.00	150	Anthropic
7	Claude Opus 5 (Bedrock)Est.	1504	$11.00	137	AWS Bedrock
8	Claude Opus 5 (India) (Bedrock)Est.	1504	$11.00	137	AWS Bedrock
9	muse-wonder	1499	$8.00	187	Meta
10	Gemini 3.8 FlashBest value	1498	$1.50	999	Google
11	Claude Opus 4.6	1496	$10.00	150	Anthropic
12	Claude Fable 5	1492	$20.00	75	Anthropic
13	Claude Fable 5 (Bedrock)Est.	1492	$20.00	75	AWS Bedrock
14	MiMo-V2.6-ProBest value	1491	$0.544	2742	Xiaomi
15	Muse Spark 1.3	1491	$2.00	746	Meta
16	Gemini 3.7 Flash	1489	$1.50	993	Google
17	Claude Opus 4.7	1483	$10.00	148	Anthropic
18	Claude Opus 4.7 (Bedrock)Est.	1483	$10.00	148	AWS Bedrock
19	Muse Spark 1.2	1483	$2.00	742	Meta
20	Qwen3.8 Max	1483	$3.00	494	Alibaba
21	Gemini 3.6 Flash	1480	$1.50	987	Google
22	Gemini 3.1 Pro Preview	1480	$2.69	551	Google
23	Gemini 3.5 Flash	1478	$3.38	438	Google
24	Muse Spark 1.1	1478	$2.00	739	Meta
25	Kimi K3	1476	$6.00	246	Moonshot AI
26	Kimi K3 (Bedrock)Est.	1476	$6.00	246	AWS Bedrock
27	Qwen3.7 Max	1475	$3.75	393	Alibaba
28	GLM-5.3	1474	$1.94	759	Z.ai (Zhipu AI)
29	Claude Sonnet 5.5	1473	$4.00	368	Anthropic
30	Claude Sonnet 5.5 (Bedrock)Est.	1473	$4.40	335	AWS Bedrock
31	GLM-5.3-FlashBest value	1473	$0.194	7584	Z.ai (Zhipu AI)
32	GLM-5.2	1470	$2.15	684	Z.ai (Zhipu AI)
33	GPT-5.5	1467	$11.25	130	OpenAI
34	GPT-5.5 (Bedrock)Est.	1467	$12.38	119	AWS Bedrock
35	DeepSeek V4.1 FlashBest value	1465	$0.052	27905	DeepSeek
36	MiMo-V2.5-Pro	1464	$0.544	2692	Xiaomi
37	GLM-5.1	1463	$2.15	680	Z.ai (Zhipu AI)
38	Claude Sonnet 4.6	1458	$6.00	243	Anthropic
39	Anthropic Claude Sonnet 4.6 (Bedrock)Est.	1458	$6.60	221	AWS Bedrock
40	Gemini 2.5 Pro	1458	$3.44	424	Google
41	GPT-5.6 Sol	1457	$8.00	182	OpenAI
42	GPT-5.6 Sol (Bedrock)Est.	1457	$11.25	130	AWS Bedrock
43	Kimi K2.6	1456	$1.71	850	Moonshot AI
44	Qwen3.7 Plus	1455	$0.700	2079	Alibaba
45	Claude Opus 4.8	1454	$10.00	145	Anthropic
46	Claude Opus 4.8 (Bedrock)Est.	1454	$10.00	145	AWS Bedrock
47	GPT-5.4	1452	$5.63	258	OpenAI
48	GPT-5.4 (Bedrock)Est.	1452	$6.19	235	AWS Bedrock
49	MiMo-V2.6-Flash	1451	$0.175	8291	Xiaomi
50	Grok 4.20	1451	$1.56	929	xAI
51	Grok 4.5	1448	$3.00	483	xAI
52	Claude Opus 4.5 (latest)	1448	$10.00	145	Anthropic
53	GPT-5.6 Terra	1448	$4.50	322	OpenAI
54	GPT-5.6 Terra (Bedrock)Est.	1448	$5.63	257	AWS Bedrock
55	GPT-5.6 Terra (India) (Bedrock)Est.	1448	$4.95	293	AWS Bedrock
56	GLM-5	1446	$1.55	933	Z.ai (Zhipu AI)
57	GLM-5 (Bedrock)Est.	1446	$1.55	933	AWS Bedrock
58	GPT-6.1 Sol	1446	$4.00	362	OpenAI
59	GPT-6.1 Sol (Bedrock)Est.	1446	$4.00	362	AWS Bedrock
60	DeepSeek V4 Pro	1445	$0.990	1460	DeepSeek
61	NVIDIA Nemotron 3 Ultra	1445	$0.912	1584	Nvidia
62	Claude Sonnet 5	1443	$4.00	361	Anthropic
63	Claude Sonnet 5 (Bedrock)Est.	1443	$4.00	361	AWS Bedrock
64	Claude Sonnet 5 (India) (Bedrock)Est.	1443	$4.40	328	AWS Bedrock
65	Gemini 3 Flash	1442	$0.909	1586	Google
66	GPT-6 Astra	1441	$20.00	72	OpenAI
67	GPT-6 Astra (Bedrock)Est.	1441	$22.00	66	AWS Bedrock
68	GLM-4.6	1440	$1.00	1440	Z.ai (Zhipu AI)
69	GLM-5V-Turbo	1438	$1.90	757	Z.ai (Zhipu AI)
70	Qwen3.5 397B-A17B	1438	$1.35	1065	Alibaba
71	Qwen3.8 27B	1438	$0.114	12642	Alibaba
72	Qwen3.6 Plus	1436	$1.13	1276	Alibaba
73	MiMo-V2-Pro	1436	$0.544	2641	Xiaomi
74	GLM-4.7	1435	$1.00	1435	Z.ai (Zhipu AI)
75	GLM-4.7 (Bedrock)Est.	1435	$1.00	1435	AWS Bedrock
76	Gemini 3.5 Flash Lite	1435	$0.850	1688	Google
77	Claude Sonnet 4.5 (latest)	1434	$6.00	239	Anthropic
78	MiniMax-M3	1431	$0.525	2726	MiniMax
79	GPT-5.6 Luna	1431	$0.450	3180	OpenAI
80	GPT-5.6 Luna (Bedrock)Est.	1431	$2.25	636	AWS Bedrock
81	GPT-5.6 Luna (India) (Bedrock)Est.	1431	$0.495	2891	AWS Bedrock
82	GLM-4.5	1430	$1.00	1430	Z.ai (Zhipu AI)
83	Mistral Large 4	1430	$1.05	1362	Mistral AI
84	Grok 4.6	1429	$3.00	476	xAI
85	Mistral Large 3	1428	$0.750	1904	Mistral AI
86	MiMo-V2.5	1428	$0.175	8160	Xiaomi
87	Mistral Medium 3.1	1424	$0.800	1780	Mistral AI
88	DeepSeek V4 Flash	1424	$0.262	5425	DeepSeek
89	MiMo-V2-Omni	1423	$0.175	8131	Xiaomi
90	GPT-5.1	1422	$3.44	414	OpenAI
91	Mistral Medium 3.5	1421	$3.00	474	Mistral AI
92	DeepSeek V3.2	1420	$0.315	4508	DeepSeek
93	Kimi K2.5	1420	$1.20	1183	Moonshot AI
94	Kimi K2.5 (Bedrock)Est.	1420	$1.20	1183	AWS Bedrock
95	Qwen3 VL 235B A22B Instruct	1420	$0.370	3838	Alibaba
96	Claude Opus 4.1 (latest)	1419	$30.00	47	Anthropic
97	Qwen3.5 122B-A10B	1418	$1.10	1289	Alibaba
98	Qwen3-Next 80B-A3B Instruct	1417	$0.875	1619	Alibaba
99	DeepSeek V3.1	1417	$0.320	4428	DeepSeek
100	DeepSeek V3.1 Terminus	1417	$0.362	3909	DeepSeek
101	Gemini 3.1 Flash Lite	1416	$0.563	2517	Google
102	Kimi K2 Thinking Turbo	1414	$2.86	494	Moonshot AI
103	Qwen3 Max	1413	$2.40	589	Alibaba
104	GPT-5.2	1412	$4.81	293	OpenAI
105	GPT-5.4 mini	1412	$1.69	837	OpenAI
106	Grok 4	1411	$6.00	235	xAI
107	o3	1410	$3.50	403	OpenAI
108	Qwen3.5 27B	1409	$0.825	1708	Alibaba
109	GPT-5	1406	$3.44	409	OpenAI
110	Gemini 2.5 Flash	1406	$0.850	1654	Google
111	MiniMax-M2.7	1405	$0.525	2676	MiniMax
112	Step 3.5 Flash	1403	$0.150	9353	StepFun
113	Hunyuan Hy3	1401	$0.350	4003	Tencent
114	Claude Haiku 5.5	1401	$0.200	7005	Anthropic
115	Claude Haiku 5.5 (Bedrock)Est.	1401	$0.220	6368	AWS Bedrock
116	Amazon Nova Premier	1400	$5.00	280	AWS Bedrock
117	Qwen3-VL 235B-A22B	1400	$1.22	1143	Alibaba
118	Qwen/Qwen3-VL-235B-A22B-Instruct (Bedrock)Est.	1400	$1.06	1318	AWS Bedrock
119	Grok 4.7	1398	$3.00	466	xAI
120	Claude Haiku 4.5	1397	$2.00	699	Anthropic
121	Grok 4.3	1397	$1.56	894	xAI
122	GPT-6 Sol	1397	$4.00	349	OpenAI
123	GPT-6 Sol (Bedrock)Est.	1397	$4.40	318	AWS Bedrock
124	Qwen3.5 Flash	1397	$0.175	7983	Alibaba
125	MiMo-V2-Flash	1395	$0.175	7971	Xiaomi
126	Qwen3.5 35B-A3B	1395	$0.688	2029	Alibaba
127	MiniMax-M2.1	1392	$0.525	2651	MiniMax
128	MiniMax M2.1 (Bedrock)Est.	1392	$0.525	2651	AWS Bedrock
129	GPT-6 Luna	1389	$0.200	6945	OpenAI
130	GPT-6 Luna (Bedrock)Est.	1389	$0.220	6314	AWS Bedrock
131	GLM-4.5-Air	1384	$0.425	3256	Z.ai (Zhipu AI)
132	GPT-4.1	1383	$3.50	395	OpenAI
133	GLM-4.6V	1376	$0.450	3058	Z.ai (Zhipu AI)
134	GPT-5 Mini	1373	$0.688	1997	OpenAI
135	DeepSeek R1	1373	$0.920	1492	DeepSeek
136	GPT-5.4 nano	1372	$0.463	2966	OpenAI
137	Kimi K2 Thinking	1371	$1.08	1275	Moonshot AI
138	Kimi K2 Thinking (Bedrock)Est.	1371	$1.08	1275	AWS Bedrock
139	Kimi K2	1371	$0.925	1482	Moonshot AI
140	Mistral Medium 3	1370	$0.800	1713	Google
141	Gemini 2.5 Flash-Lite	1369	$0.175	7823	Google
142	Qwen3-Next 80B-A3B (Thinking)	1368	$1.88	730	Alibaba
143	Qwen3 235B-A22B	1366	$1.22	1115	Alibaba
144	GPT OSS 120BBest value	1365	$0.017	81493	OpenAI
145	gpt-oss-120b (Bedrock)Est.	1365	$0.262	5200	AWS Bedrock
146	Llama 4 Maverick	1360	$0.378	3603	Meta
147	MiniMax-M2.5	1359	$0.525	2589	MiniMax
148	MiniMax M2.5 (Bedrock)Est.	1359	$0.525	2589	AWS Bedrock
149	Gemma 3 27B IT	1358	$0.100	13580	Google
150	Google Gemma 3 27B Instruct (Bedrock)Est.	1358	$0.268	5077	AWS Bedrock
151	Qwen3-Coder 480B-A35B Instruct	1357	$3.00	452	Alibaba
152	Gemini 2.0 Flash	1354	$0.175	7737	Google
153	o4-mini	1353	$1.93	703	OpenAI
154	o1	1353	$26.25	52	OpenAI
155	GLM-4.7-Flash	1351	$0.145	9317	Z.ai (Zhipu AI)
156	GLM-4.7-Flash (Bedrock)Est.	1351	$0.153	8859	AWS Bedrock
157	Amazon Nova Pro	1348	$1.40	963	AWS Bedrock
158	nvidia-nemotron-3-nano-30b-a3b	1348	$0.088	15406	Nvidia
159	MiniMax M1	1343	$0.412	3256	MiniMax
160	GPT-4.1 Mini	1340	$0.700	1914	OpenAI
161	Devstral 2	1340	$0.525	2552	Mistral AI
162	MiniMax-M2	1340	$0.525	2552	MiniMax
163	MiniMax M2 (Bedrock)Est.	1340	$0.525	2552	AWS Bedrock
164	Qwen3 32B	1340	$1.22	1094	Alibaba
165	Claude Sonnet 4	1339	$5.20	258	Anthropic
166	Gemma 3 12B IT	1334	$0.060	22233	Google
167	Google Gemma 3 12B (Bedrock)Est.	1334	$0.140	9529	AWS Bedrock
168	GLM-4.5V	1333	$0.900	1481	Z.ai (Zhipu AI)
169	Llama 4 Scout	1332	$0.168	7952	Meta
170	DeepSeek V3	1332	$0.438	3045	DeepSeek
171	Command A	1331	$4.38	304	Cohere
172	Gemini 2.0 Flash-Lite	1330	$0.131	10133	Google
173	Qwen Plus	1326	$0.600	2210	Alibaba
174	Mistral Small 4	1325	$0.262	5048	Mistral AI
175	Step 2 (16K)	1321	$8.02	165	StepFun
176	GPT-5 Nano	1320	$0.138	9600	OpenAI
177	o3-mini	1319	$1.93	685	OpenAI
178	Qwen3 30B A3B	1317	$0.133	9940	Alibaba
179	Llama 3.3 70B	1315	$0.600	2192	Meta
180	Amazon Nova Lite	1298	$0.105	12362	AWS Bedrock
181	gemma-3-4b-it	1291	$0.042	30376	Google
182	Gemma 3 4B IT (Bedrock)Est.	1291	$0.050	25820	AWS Bedrock
183	GPT OSS 20BBest value	1287	$0.007	171600	OpenAI
184	gpt-oss-20b (Bedrock)Est.	1287	$0.128	10094	AWS Bedrock
185	GPT-4o mini	1286	$0.262	4899	OpenAI
186	GPT-4.1 Nano	1285	$0.175	7343	OpenAI
187	GPT-4o	1283	$4.38	293	OpenAI
188	Qwen Max	1282	$2.80	458	Alibaba
189	Llama 4 Scout 17B 16E Instruct	1279	$0.150	8527	Meta
190	Mistral Small 3.1 24B Instruct	1277	$0.150	8513	Mistral AI
191	Llama-3.3-70B-Instruct	1274	$0.198	6451	Meta
192	Qwen2.5 72B Instruct	1269	$2.45	518	Alibaba
193	Amazon Nova Micro	1268	$0.061	20702	AWS Bedrock
194	Command R7B	1262	$0.066	19230	Cohere
195	GPT-4 Turbo	1262	$15.00	84	OpenAI
196	Llama 3.1 70B Instruct	1261	$0.400	3153	Meta
197	Gemma 2 27B	1231	$0.650	1894	Google
198	Qwen2.5 Coder 32B Instruct	1230	$0.095	12947	Alibaba
199	Phi 4	1217	$0.088	13909	Microsoft
200	Command R+	1204	$4.38	275	Cohere
201	Llama 3.1 8b Instruct	1187	$0.025	47480	Meta
202	GPT-4	1186	$37.50	32	OpenAI
203	Mistral Large	1176	$3.00	392	Mistral AI
204	Command R	1163	$0.262	4430	Cohere
205	Llama 3.2 3B Instruct	1110	$0.020	55500	Meta
206	GPT-3.5-turbo	1094	$0.750	1459	OpenAI
207	Llama 3.2 1B Instruct	1055	$0.010	105500	Meta

Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 2 November 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.

Download / cite this dataset

The full ranking is available as open data — reuse it with attribution and a link back.

Download JSON Download CSV

Cite as: AI Calculator Pro, “LLM intelligence per dollar”, https://aicalculatorpro.com/intelligence/ (snapshot 2026-11-02). Underlying scores LMArena / arena.ai, CC BY 4.0.

FAQ

What does the Arena score mean?

It is a community Elo rating from blind, head-to-head votes: users compare two anonymous model answers and pick the better one. A higher score means the model is preferred more often. It measures human preference, not correctness on any single benchmark.

What is 'intelligence per dollar'?

We divide a model's Arena score by its blended price (a 3:1 input:output blend, $ per 1M tokens). It surfaces models that punch above their price. Use it as a starting point, then confirm the model clears the quality bar your task actually needs.

Why isn't every model listed?

We only show a score when we can confidently map an Arena entry to a model we track. Models without a confident match carry no score rather than a wrong one. Scores come from LMArena / arena.ai and were last refreshed 2026-11-02.

What do the “Measured” and “Estimated” labels mean?

Measured means the Arena leaderboard voted on that exact model. Estimated means the model is a regional or creator-prefixed hosting listing of a base model (for example an AWS Bedrock “jp.anthropic.…” profile) — the weights are identical, so we inherit the base model's score, but Arena never voted on that specific listing. We label it rather than hide it, so you always know whether a score is direct or inherited.

Cite / link to this page

You’re welcome to reference this page and its figures with attribution and a link back.

https://aicalculatorpro.com/intelligence/

<a href="https://aicalculatorpro.com/intelligence/">Intelligence per dollar — LLM rankings — AI Calculator Pro</a>