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).
The highest-scoring model we track for this arena — the quality ceiling.
The most Arena score per dollar — punches far above its price.
The lowest price among models still within 15% of the top Arena score.
The biggest context window among genuinely capable models — for long docs and codebases.
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.
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.
| 1 | Claude Opus 5Best value | 1505 | $10.00 | 151 | Anthropic |
| 2 | Claude Opus 5 (Bedrock)Est. | 1505 | $11.00 | 137 | AWS Bedrock |
| 3 | Claude Opus 4.6 | 1498 | $10.00 | 150 | Anthropic |
| 4 | Gemini 3.8 FlashBest value | 1495 | $1.50 | 997 | |
| 5 | Claude Fable 5 | 1493 | $20.00 | 75 | Anthropic |
| 6 | Claude Fable 5 (Bedrock)Est. | 1493 | $20.00 | 75 | AWS Bedrock |
| 7 | Gemini 3.7 Flash | 1490 | $1.50 | 993 | |
| 8 | Muse Spark 1.2 | 1489 | $2.00 | 745 | Meta |
| 9 | Claude Opus 4.7 | 1483 | $10.00 | 148 | Anthropic |
| 10 | Claude Opus 4.7 (Bedrock)Est. | 1483 | $10.00 | 148 | AWS Bedrock |
| 11 | Qwen3.8 Max | 1481 | $3.00 | 494 | Alibaba |
| 12 | Muse Spark 1.1 | 1480 | $2.00 | 740 | Meta |
| 13 | Gemini 3.1 Pro Preview | 1480 | $4.50 | 329 | |
| 14 | Gemini 3.5 Flash | 1476 | $3.38 | 437 | |
| 15 | Gemini 3.6 Flash | 1476 | $1.50 | 984 | |
| 16 | Qwen3.7 Max | 1474 | $3.75 | 393 | Alibaba |
| 17 | Kimi K3 | 1473 | $6.00 | 246 | Moonshot AI |
| 18 | GLM-5.3-FlashBest value | 1472 | $0.119 | 12396 | Z.ai (Zhipu AI) |
| 19 | GPT-5.5 | 1466 | $11.25 | 130 | OpenAI |
| 20 | GPT-5.5 (Bedrock)Est. | 1466 | $12.38 | 118 | AWS Bedrock |
| 21 | MiMo-V2.5-Pro | 1465 | $0.544 | 2694 | Xiaomi |
| 22 | GLM-5.2 | 1463 | $2.15 | 680 | Z.ai (Zhipu AI) |
| 23 | GLM-5.1 | 1462 | $2.15 | 680 | Z.ai (Zhipu AI) |
| 24 | Claude Sonnet 4.6 | 1458 | $6.00 | 243 | Anthropic |
| 25 | Anthropic Claude Sonnet 4.6 (Bedrock)Est. | 1458 | $6.60 | 221 | AWS Bedrock |
| 26 | Gemini 2.5 Pro | 1458 | $3.44 | 424 | |
| 27 | GPT-5.6 Sol | 1455 | $8.00 | 182 | OpenAI |
| 28 | GPT-5.6 Sol (Bedrock)Est. | 1455 | $11.25 | 129 | AWS Bedrock |
| 29 | Kimi K2.6 | 1455 | $1.71 | 850 | Moonshot AI |
| 30 | Qwen3.7 Plus | 1454 | $1.13 | 1292 | Alibaba |
| 31 | GPT-5.4 | 1453 | $5.63 | 258 | OpenAI |
| 32 | GPT-5.4 (Bedrock)Est. | 1453 | $6.19 | 235 | AWS Bedrock |
| 33 | Claude Opus 4.8 | 1453 | $10.00 | 145 | Anthropic |
| 34 | Claude Opus 4.8 (Bedrock)Est. | 1453 | $10.00 | 145 | AWS Bedrock |
| 35 | Grok 4.5 | 1450 | $3.00 | 483 | xAI |
| 36 | Claude Opus 4.5 (latest) | 1450 | $10.00 | 145 | Anthropic |
| 37 | GLM-5 | 1446 | $1.55 | 933 | Z.ai (Zhipu AI) |
| 38 | GLM-5 (Bedrock)Est. | 1446 | $1.55 | 933 | AWS Bedrock |
| 39 | GPT-5.6 Terra | 1446 | $4.50 | 321 | OpenAI |
| 40 | GPT-5.6 Terra (Bedrock)Est. | 1446 | $5.63 | 257 | AWS Bedrock |
| 41 | Kimi K2.5 | 1446 | $1.20 | 1205 | Moonshot AI |
| 42 | Kimi K2.5 (Bedrock)Est. | 1446 | $1.20 | 1205 | AWS Bedrock |
| 43 | GPT-5.6 Terra (India) (Bedrock)Est. | 1446 | $4.95 | 292 | AWS Bedrock |
| 44 | DeepSeek V4 Pro | 1444 | $0.544 | 2656 | DeepSeek |
| 45 | Claude Sonnet 5 | 1442 | $4.00 | 361 | Anthropic |
| 46 | Claude Sonnet 5 (Bedrock)Est. | 1442 | $4.00 | 361 | AWS Bedrock |
| 47 | Gemini 3 Flash | 1442 | $0.900 | 1602 | |
| 48 | Hunyuan Hy3 | 1441 | $0.350 | 4117 | Tencent |
| 49 | GLM-4.6 | 1440 | $1.00 | 1440 | Z.ai (Zhipu AI) |
| 50 | Qwen3 Max | 1439 | $2.40 | 600 | Alibaba |
| 51 | Qwen3.8 27B | 1439 | $0.147 | 9756 | Alibaba |
| 52 | Claude Sonnet 4.5 (latest) | 1438 | $6.00 | 240 | Anthropic |
| 53 | Qwen3.5 397B-A17B | 1438 | $1.35 | 1065 | Alibaba |
| 54 | Qwen3.6 Plus | 1437 | $1.13 | 1277 | Alibaba |
| 55 | GLM-4.7 | 1436 | $1.00 | 1436 | Z.ai (Zhipu AI) |
| 56 | GLM-4.7 (Bedrock)Est. | 1436 | $1.00 | 1436 | AWS Bedrock |
| 57 | GLM-5V-Turbo | 1436 | $1.90 | 756 | Z.ai (Zhipu AI) |
| 58 | MiMo-V2-Pro | 1436 | $0.544 | 2641 | Xiaomi |
| 59 | Gemini 3.5 Flash Lite | 1436 | $0.850 | 1689 | |
| 60 | MiniMax-M3 | 1433 | $0.525 | 2730 | MiniMax |
| 61 | GLM-4.5 | 1430 | $1.00 | 1430 | Z.ai (Zhipu AI) |
| 62 | GPT-5.6 Luna | 1430 | $0.450 | 3178 | OpenAI |
| 63 | GPT-5.6 Luna (Bedrock)Est. | 1430 | $2.25 | 636 | AWS Bedrock |
| 64 | Grok 4.6 | 1430 | $3.00 | 477 | xAI |
| 65 | GPT-5.6 Luna (India) (Bedrock)Est. | 1430 | $0.495 | 2889 | AWS Bedrock |
| 66 | Mistral Large 3 | 1427 | $0.750 | 1903 | Mistral AI |
| 67 | MiMo-V2.5 | 1427 | $0.175 | 8154 | Xiaomi |
| 68 | DeepSeek V4 Flash | 1424 | $0.262 | 5425 | DeepSeek |
| 69 | GPT-5.1 | 1423 | $3.44 | 414 | OpenAI |
| 70 | o3 | 1422 | $3.50 | 406 | OpenAI |
| 71 | MiMo-V2-Omni | 1422 | $0.175 | 8126 | Xiaomi |
| 72 | mistral-medium-3-5 | 1421 | $3.00 | 474 | Mistral AI |
| 73 | Qwen3 VL 235B A22B Instruct | 1421 | $0.370 | 3841 | Alibaba |
| 74 | DeepSeek V3.2 | 1420 | $0.315 | 4508 | DeepSeek |
| 75 | Claude Opus 4.1 (latest) | 1418 | $30.00 | 47 | Anthropic |
| 76 | Qwen3.5 122B-A10B | 1418 | $1.10 | 1289 | Alibaba |
| 77 | Qwen3-Next 80B-A3B Instruct | 1418 | $0.875 | 1621 | Alibaba |
| 78 | Gemini 2.5 Flash | 1417 | $0.850 | 1667 | |
| 79 | DeepSeek V3.1 | 1417 | $0.320 | 4428 | DeepSeek |
| 80 | DeepSeek V3.1 Terminus | 1417 | $0.362 | 3909 | DeepSeek |
| 81 | Gemini 3.1 Flash Lite | 1415 | $0.563 | 2516 | |
| 82 | Kimi K2 Thinking Turbo | 1414 | $2.86 | 494 | Moonshot AI |
| 83 | GPT-5.2 | 1412 | $4.81 | 293 | OpenAI |
| 84 | GPT-5.4 mini | 1412 | $1.69 | 837 | OpenAI |
| 85 | Grok 4 | 1412 | $6.00 | 235 | xAI |
| 86 | Qwen3.5 27B | 1408 | $0.825 | 1707 | Alibaba |
| 87 | GPT-5 | 1406 | $3.44 | 409 | OpenAI |
| 88 | MiniMax-M2.7 | 1405 | $0.525 | 2676 | MiniMax |
| 89 | Step 3.5 Flash | 1404 | $0.150 | 9360 | StepFun |
| 90 | Qwen3-VL 235B-A22B | 1401 | $1.22 | 1144 | Alibaba |
| 91 | Qwen/Qwen3-VL-235B-A22B-Instruct (Bedrock)Est. | 1401 | $1.06 | 1319 | AWS Bedrock |
| 92 | Qwen3 VL 235B A22B Thinking | 1401 | $0.932 | 1503 | Alibaba |
| 93 | Amazon Nova Premier | 1400 | $5.00 | 280 | AWS Bedrock |
| 94 | Grok 4.3 | 1398 | $1.56 | 895 | xAI |
| 95 | Qwen3.5 FlashBest value | 1398 | $0.093 | 14952 | Alibaba |
| 96 | Claude Haiku 4.5 | 1397 | $2.00 | 699 | Anthropic |
| 97 | Qwen3.5 35B-A3B | 1395 | $0.688 | 2029 | Alibaba |
| 98 | MiMo-V2-Flash | 1394 | $0.175 | 7966 | Xiaomi |
| 99 | MiniMax-M2.1 | 1391 | $0.525 | 2650 | MiniMax |
| 100 | MiniMax M2.1 (Bedrock)Est. | 1391 | $0.525 | 2650 | AWS Bedrock |
| 101 | GLM-4.5-Air | 1384 | $0.425 | 3256 | Z.ai (Zhipu AI) |
| 102 | o4-mini | 1382 | $1.93 | 718 | OpenAI |
| 103 | GLM-4.6V | 1377 | $0.450 | 3060 | Z.ai (Zhipu AI) |
| 104 | GPT-5 Mini | 1373 | $0.688 | 1997 | OpenAI |
| 105 | GPT-5.4 nano | 1373 | $0.463 | 2969 | OpenAI |
| 106 | DeepSeek R1 | 1373 | $0.725 | 1894 | DeepSeek |
| 107 | GPT-4.1 | 1372 | $3.50 | 392 | OpenAI |
| 108 | Kimi K2 Thinking | 1371 | $1.08 | 1275 | Moonshot AI |
| 109 | Kimi K2 Thinking (Bedrock)Est. | 1371 | $1.08 | 1275 | AWS Bedrock |
| 110 | Kimi K2 | 1371 | $0.925 | 1482 | Moonshot AI |
| 111 | Qwen3-Next 80B-A3B (Thinking) | 1368 | $1.88 | 730 | Alibaba |
| 112 | GPT OSS 120BBest value | 1366 | $0.059 | 23153 | OpenAI |
| 113 | gpt-oss-120b (Bedrock)Est. | 1366 | $0.262 | 5204 | AWS Bedrock |
| 114 | Qwen3 235B-A22B | 1366 | $1.22 | 1115 | Alibaba |
| 115 | Claude 4 Opus | 1366 | $25.75 | 53 | Anthropic |
| 116 | Command A | 1365 | $4.38 | 312 | Cohere |
| 117 | Llama 4 Maverick | 1360 | $0.378 | 3603 | Meta |
| 118 | MiniMax-M2.5 | 1359 | $0.525 | 2589 | MiniMax |
| 119 | MiniMax M2.5 (Bedrock)Est. | 1359 | $0.525 | 2589 | AWS Bedrock |
| 120 | Gemma 3 27B IT | 1358 | $0.100 | 13580 | |
| 121 | Google Gemma 3 27B Instruct (Bedrock)Est. | 1358 | $0.268 | 5077 | AWS Bedrock |
| 122 | Qwen3-Coder 480B-A35B Instruct | 1356 | $3.00 | 452 | Alibaba |
| 123 | GPT-4o | 1355 | $4.38 | 310 | OpenAI |
| 124 | Gemini 2.0 Flash | 1354 | $0.175 | 7737 | |
| 125 | o1 | 1353 | $26.25 | 52 | OpenAI |
| 126 | GLM-4.7-Flash | 1352 | $0.145 | 9324 | Z.ai (Zhipu AI) |
| 127 | GLM-4.7-Flash (Bedrock)Est. | 1352 | $0.153 | 8866 | AWS Bedrock |
| 128 | Mistral Medium 3.1 | 1350 | $0.800 | 1688 | Mistral AI |
| 129 | Amazon Nova Pro | 1348 | $1.40 | 963 | AWS Bedrock |
| 130 | GPT-4.1 Mini | 1345 | $0.700 | 1921 | OpenAI |
| 131 | MiniMax M1 | 1343 | $0.412 | 3256 | MiniMax |
| 132 | MiniMax-M2 | 1342 | $0.525 | 2556 | MiniMax |
| 133 | MiniMax M2 (Bedrock)Est. | 1342 | $0.525 | 2556 | AWS Bedrock |
| 134 | Devstral 2 | 1340 | $0.525 | 2552 | Mistral AI |
| 135 | Qwen3 32B | 1340 | $1.22 | 1094 | Alibaba |
| 136 | Claude 4 Sonnet | 1339 | $5.20 | 258 | Anthropic |
| 137 | o3 Mini High | 1337 | $1.74 | 767 | OpenAI |
| 138 | Gemma 3 12B IT | 1334 | $0.063 | 21344 | |
| 139 | Google Gemma 3 12B (Bedrock)Est. | 1334 | $0.140 | 9529 | AWS Bedrock |
| 140 | GLM-4.5V | 1333 | $0.900 | 1481 | Z.ai (Zhipu AI) |
| 141 | Llama 4 Scout | 1332 | $0.168 | 7952 | Meta |
| 142 | DeepSeek V3 | 1332 | $0.438 | 3045 | DeepSeek |
| 143 | Gemini 2.5 Flash-Lite | 1330 | $0.175 | 7600 | |
| 144 | Qwen Plus | 1326 | $0.600 | 2210 | Alibaba |
| 145 | Mistral Small 4 | 1325 | $0.262 | 5048 | Mistral AI |
| 146 | Step 2 (16K) | 1321 | $8.02 | 165 | StepFun |
| 147 | GPT-5 Nano | 1320 | $0.138 | 9600 | OpenAI |
| 148 | o3-mini | 1319 | $1.93 | 685 | OpenAI |
| 149 | Qwen3 30B A3B | 1317 | $0.133 | 9940 | Alibaba |
| 150 | Llama 3.3 70B | 1315 | $0.600 | 2192 | Meta |
| 151 | GPT-4o mini | 1310 | $0.262 | 4990 | OpenAI |
| 152 | GPT-4.1 Nano | 1300 | $0.175 | 7429 | OpenAI |
| 153 | Amazon Nova Lite | 1298 | $0.105 | 12362 | AWS Bedrock |
| 154 | gemma-3-4b-itBest value | 1291 | $0.050 | 25820 | |
| 155 | Gemma 3 4B IT (Bedrock)Best valueEst. | 1291 | $0.050 | 25820 | AWS Bedrock |
| 156 | GPT OSS 20BBest value | 1287 | $0.040 | 32175 | OpenAI |
| 157 | gpt-oss-20b (Bedrock)Est. | 1287 | $0.128 | 10094 | AWS Bedrock |
| 158 | Qwen Max | 1282 | $2.80 | 458 | Alibaba |
| 159 | Llama 4 Scout 17B 16E Instruct | 1279 | $0.150 | 8527 | Meta |
| 160 | Mistral Small 3.1 24B Instruct | 1277 | $0.150 | 8513 | Mistral AI |
| 161 | Llama-3.3-70B-Instruct | 1274 | $0.155 | 8219 | Meta |
| 162 | Qwen2.5 72B Instruct | 1269 | $2.45 | 518 | Alibaba |
| 163 | Amazon Nova Micro | 1268 | $0.061 | 20702 | AWS Bedrock |
| 164 | Command R7B | 1262 | $0.066 | 19230 | Cohere |
| 165 | Llama 3.1 70B Instruct | 1261 | $0.400 | 3153 | Meta |
| 166 | Claude 3.5 Haiku | 1255 | $1.60 | 784 | Anthropic |
| 167 | Qwen2.5-Coder 32B Instruct | 1230 | $0.095 | 12947 | Alibaba |
| 168 | Llama 3 70B Instruct | 1221 | $0.568 | 2152 | Meta |
| 169 | Phi 4 | 1217 | $0.088 | 13909 | Microsoft |
| 170 | Command R+ | 1204 | $4.38 | 275 | Cohere |
| 171 | Claude Haiku 3 | 1195 | $0.500 | 2390 | Anthropic |
| 172 | GPT-4 | 1186 | $37.50 | 32 | OpenAI |
| 173 | Llama 3.1 8b InstructBest value | 1186 | $0.025 | 47440 | Meta |
| 174 | Mistral Large | 1176 | $3.00 | 392 | Mistral AI |
| 175 | Command R | 1163 | $0.262 | 4430 | Cohere |
| 176 | QwQ 32B | 1162 | $0.400 | 2905 | Alibaba |
| 177 | Llama 3.2 3b InstructBest value | 1109 | $0.020 | 55450 | Meta |
| 178 | GPT-3.5-turbo | 1094 | $0.750 | 1459 | OpenAI |
| 179 | Llama 3.2 1B InstructBest value | 1055 | $0.010 | 105500 | Meta |
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>