AI Calculator Pro

Intelligence per dollar

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.

Decision-ready picks

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

Best overall
Claude Opus 5
Anthropic · Arena 1505

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

Best value
Llama 3.2 1B Instruct
Meta · 105500 Elo per $/1M

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

Cheapest that clears the bar
GPT OSS 20B
OpenAI · $0.040/1M 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
Kimi K3
Moonshot AI · Coding Arena 1679

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.
1168128013931505$0.050$0.100$0.250$0.500$1.00$2.00$5.00$10$25Blended price $/1M (log scale) →Arena score →gemma-3-4b-itGemma 3 4B IT (Bedrock)GPT OSS 120BGPT OSS 20BClaude Opus 5Gemini 3.8 FlashGLM-5.3-FlashLlama 3.1 8b InstructLlama 3.2 1B InstructLlama 3.2 3b InstructQwen3.5 Flash

11 of 179 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.

1Claude Opus 5Best value1505$10.00151Anthropic
2Claude Opus 5 (Bedrock)Est.1505$11.00137AWS Bedrock
3Claude Opus 4.61498$10.00150Anthropic
4Gemini 3.8 FlashBest value1495$1.50997Google
5Claude Fable 51493$20.0075Anthropic
6Claude Fable 5 (Bedrock)Est.1493$20.0075AWS Bedrock
7Gemini 3.7 Flash1490$1.50993Google
8Muse Spark 1.21489$2.00745Meta
9Claude Opus 4.71483$10.00148Anthropic
10Claude Opus 4.7 (Bedrock)Est.1483$10.00148AWS Bedrock
11Qwen3.8 Max1481$3.00494Alibaba
12Muse Spark 1.11480$2.00740Meta
13Gemini 3.1 Pro Preview1480$4.50329Google
14Gemini 3.5 Flash1476$3.38437Google
15Gemini 3.6 Flash1476$1.50984Google
16Qwen3.7 Max1474$3.75393Alibaba
17Kimi K31473$6.00246Moonshot AI
18GLM-5.3-FlashBest value1472$0.11912396Z.ai (Zhipu AI)
19GPT-5.51466$11.25130OpenAI
20GPT-5.5 (Bedrock)Est.1466$12.38118AWS Bedrock
21MiMo-V2.5-Pro1465$0.5442694Xiaomi
22GLM-5.21463$2.15680Z.ai (Zhipu AI)
23GLM-5.11462$2.15680Z.ai (Zhipu AI)
24Claude Sonnet 4.61458$6.00243Anthropic
25Anthropic Claude Sonnet 4.6 (Bedrock)Est.1458$6.60221AWS Bedrock
26Gemini 2.5 Pro1458$3.44424Google
27GPT-5.6 Sol1455$8.00182OpenAI
28GPT-5.6 Sol (Bedrock)Est.1455$11.25129AWS Bedrock
29Kimi K2.61455$1.71850Moonshot AI
30Qwen3.7 Plus1454$1.131292Alibaba
31GPT-5.41453$5.63258OpenAI
32GPT-5.4 (Bedrock)Est.1453$6.19235AWS Bedrock
33Claude Opus 4.81453$10.00145Anthropic
34Claude Opus 4.8 (Bedrock)Est.1453$10.00145AWS Bedrock
35Grok 4.51450$3.00483xAI
36Claude Opus 4.5 (latest)1450$10.00145Anthropic
37GLM-51446$1.55933Z.ai (Zhipu AI)
38GLM-5 (Bedrock)Est.1446$1.55933AWS Bedrock
39GPT-5.6 Terra1446$4.50321OpenAI
40GPT-5.6 Terra (Bedrock)Est.1446$5.63257AWS Bedrock
41Kimi K2.51446$1.201205Moonshot AI
42Kimi K2.5 (Bedrock)Est.1446$1.201205AWS Bedrock
43GPT-5.6 Terra (India) (Bedrock)Est.1446$4.95292AWS Bedrock
44DeepSeek V4 Pro1444$0.5442656DeepSeek
45Claude Sonnet 51442$4.00361Anthropic
46Claude Sonnet 5 (Bedrock)Est.1442$4.00361AWS Bedrock
47Gemini 3 Flash1442$0.9001602Google
48Hunyuan Hy31441$0.3504117Tencent
49GLM-4.61440$1.001440Z.ai (Zhipu AI)
50Qwen3 Max1439$2.40600Alibaba
51Qwen3.8 27B1439$0.1479756Alibaba
52Claude Sonnet 4.5 (latest)1438$6.00240Anthropic
53Qwen3.5 397B-A17B1438$1.351065Alibaba
54Qwen3.6 Plus1437$1.131277Alibaba
55GLM-4.71436$1.001436Z.ai (Zhipu AI)
56GLM-4.7 (Bedrock)Est.1436$1.001436AWS Bedrock
57GLM-5V-Turbo1436$1.90756Z.ai (Zhipu AI)
58MiMo-V2-Pro1436$0.5442641Xiaomi
59Gemini 3.5 Flash Lite1436$0.8501689Google
60MiniMax-M31433$0.5252730MiniMax
61GLM-4.51430$1.001430Z.ai (Zhipu AI)
62GPT-5.6 Luna1430$0.4503178OpenAI
63GPT-5.6 Luna (Bedrock)Est.1430$2.25636AWS Bedrock
64Grok 4.61430$3.00477xAI
65GPT-5.6 Luna (India) (Bedrock)Est.1430$0.4952889AWS Bedrock
66Mistral Large 31427$0.7501903Mistral AI
67MiMo-V2.51427$0.1758154Xiaomi
68DeepSeek V4 Flash1424$0.2625425DeepSeek
69GPT-5.11423$3.44414OpenAI
70o31422$3.50406OpenAI
71MiMo-V2-Omni1422$0.1758126Xiaomi
72mistral-medium-3-51421$3.00474Mistral AI
73Qwen3 VL 235B A22B Instruct1421$0.3703841Alibaba
74DeepSeek V3.21420$0.3154508DeepSeek
75Claude Opus 4.1 (latest)1418$30.0047Anthropic
76Qwen3.5 122B-A10B1418$1.101289Alibaba
77Qwen3-Next 80B-A3B Instruct1418$0.8751621Alibaba
78Gemini 2.5 Flash1417$0.8501667Google
79DeepSeek V3.11417$0.3204428DeepSeek
80DeepSeek V3.1 Terminus1417$0.3623909DeepSeek
81Gemini 3.1 Flash Lite1415$0.5632516Google
82Kimi K2 Thinking Turbo1414$2.86494Moonshot AI
83GPT-5.21412$4.81293OpenAI
84GPT-5.4 mini1412$1.69837OpenAI
85Grok 41412$6.00235xAI
86Qwen3.5 27B1408$0.8251707Alibaba
87GPT-51406$3.44409OpenAI
88MiniMax-M2.71405$0.5252676MiniMax
89Step 3.5 Flash1404$0.1509360StepFun
90Qwen3-VL 235B-A22B1401$1.221144Alibaba
91Qwen/Qwen3-VL-235B-A22B-Instruct (Bedrock)Est.1401$1.061319AWS Bedrock
92Qwen3 VL 235B A22B Thinking1401$0.9321503Alibaba
93Amazon Nova Premier1400$5.00280AWS Bedrock
94Grok 4.31398$1.56895xAI
95Qwen3.5 FlashBest value1398$0.09314952Alibaba
96Claude Haiku 4.51397$2.00699Anthropic
97Qwen3.5 35B-A3B1395$0.6882029Alibaba
98MiMo-V2-Flash1394$0.1757966Xiaomi
99MiniMax-M2.11391$0.5252650MiniMax
100MiniMax M2.1 (Bedrock)Est.1391$0.5252650AWS Bedrock
101GLM-4.5-Air1384$0.4253256Z.ai (Zhipu AI)
102o4-mini1382$1.93718OpenAI
103GLM-4.6V1377$0.4503060Z.ai (Zhipu AI)
104GPT-5 Mini1373$0.6881997OpenAI
105GPT-5.4 nano1373$0.4632969OpenAI
106DeepSeek R11373$0.7251894DeepSeek
107GPT-4.11372$3.50392OpenAI
108Kimi K2 Thinking1371$1.081275Moonshot AI
109Kimi K2 Thinking (Bedrock)Est.1371$1.081275AWS Bedrock
110Kimi K21371$0.9251482Moonshot AI
111Qwen3-Next 80B-A3B (Thinking)1368$1.88730Alibaba
112GPT OSS 120BBest value1366$0.05923153OpenAI
113gpt-oss-120b (Bedrock)Est.1366$0.2625204AWS Bedrock
114Qwen3 235B-A22B1366$1.221115Alibaba
115Claude 4 Opus1366$25.7553Anthropic
116Command A1365$4.38312Cohere
117Llama 4 Maverick1360$0.3783603Meta
118MiniMax-M2.51359$0.5252589MiniMax
119MiniMax M2.5 (Bedrock)Est.1359$0.5252589AWS Bedrock
120Gemma 3 27B IT1358$0.10013580Google
121Google Gemma 3 27B Instruct (Bedrock)Est.1358$0.2685077AWS Bedrock
122Qwen3-Coder 480B-A35B Instruct1356$3.00452Alibaba
123GPT-4o1355$4.38310OpenAI
124Gemini 2.0 Flash1354$0.1757737Google
125o11353$26.2552OpenAI
126GLM-4.7-Flash1352$0.1459324Z.ai (Zhipu AI)
127GLM-4.7-Flash (Bedrock)Est.1352$0.1538866AWS Bedrock
128Mistral Medium 3.11350$0.8001688Mistral AI
129Amazon Nova Pro1348$1.40963AWS Bedrock
130GPT-4.1 Mini1345$0.7001921OpenAI
131MiniMax M11343$0.4123256MiniMax
132MiniMax-M21342$0.5252556MiniMax
133MiniMax M2 (Bedrock)Est.1342$0.5252556AWS Bedrock
134Devstral 21340$0.5252552Mistral AI
135Qwen3 32B1340$1.221094Alibaba
136Claude 4 Sonnet1339$5.20258Anthropic
137o3 Mini High1337$1.74767OpenAI
138Gemma 3 12B IT1334$0.06321344Google
139Google Gemma 3 12B (Bedrock)Est.1334$0.1409529AWS Bedrock
140GLM-4.5V1333$0.9001481Z.ai (Zhipu AI)
141Llama 4 Scout1332$0.1687952Meta
142DeepSeek V31332$0.4383045DeepSeek
143Gemini 2.5 Flash-Lite1330$0.1757600Google
144Qwen Plus1326$0.6002210Alibaba
145Mistral Small 41325$0.2625048Mistral AI
146Step 2 (16K)1321$8.02165StepFun
147GPT-5 Nano1320$0.1389600OpenAI
148o3-mini1319$1.93685OpenAI
149Qwen3 30B A3B1317$0.1339940Alibaba
150Llama 3.3 70B1315$0.6002192Meta
151GPT-4o mini1310$0.2624990OpenAI
152GPT-4.1 Nano1300$0.1757429OpenAI
153Amazon Nova Lite1298$0.10512362AWS Bedrock
154gemma-3-4b-itBest value1291$0.05025820Google
155Gemma 3 4B IT (Bedrock)Best valueEst.1291$0.05025820AWS Bedrock
156GPT OSS 20BBest value1287$0.04032175OpenAI
157gpt-oss-20b (Bedrock)Est.1287$0.12810094AWS Bedrock
158Qwen Max1282$2.80458Alibaba
159Llama 4 Scout 17B 16E Instruct1279$0.1508527Meta
160Mistral Small 3.1 24B Instruct1277$0.1508513Mistral AI
161Llama-3.3-70B-Instruct1274$0.1558219Meta
162Qwen2.5 72B Instruct1269$2.45518Alibaba
163Amazon Nova Micro1268$0.06120702AWS Bedrock
164Command R7B1262$0.06619230Cohere
165Llama 3.1 70B Instruct1261$0.4003153Meta
166Claude 3.5 Haiku1255$1.60784Anthropic
167Qwen2.5-Coder 32B Instruct1230$0.09512947Alibaba
168Llama 3 70B Instruct1221$0.5682152Meta
169Phi 41217$0.08813909Microsoft
170Command R+1204$4.38275Cohere
171Claude Haiku 31195$0.5002390Anthropic
172GPT-41186$37.5032OpenAI
173Llama 3.1 8b InstructBest value1186$0.02547440Meta
174Mistral Large1176$3.00392Mistral AI
175Command R1163$0.2624430Cohere
176QwQ 32B1162$0.4002905Alibaba
177Llama 3.2 3b InstructBest value1109$0.02055450Meta
178GPT-3.5-turbo1094$0.7501459OpenAI
179Llama 3.2 1B InstructBest value1055$0.010105500Meta

Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 18 September 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.

Cite as: AI Calculator Pro, “LLM intelligence per dollar”, https://aicalculatorpro.com/intelligence/ (snapshot 2026-09-18). 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 2026-09-18.

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>