Best value LLMs: most intelligence per dollar
Every LLM value ranking divides quality by the price the lab publishes. But the same model is resold by dozens of providers, often for a fraction of that — so the list price answers “is this vendor’s price fair?”, not “where do I get the most intelligence per dollar?”. This table ranks 188 scored models by Arena score against the cheapest price a major provider charges for them — first-party vendors, the big clouds, and established hosts like OpenRouter, DeepInfra, Together, Fireworks and Groq. Drawn from 6,947 offerings across 1,873 models, rebuilt daily.
Qwen3.8 27B — 12,668 Elo per $/1M
The most Arena score per dollar among models within 5% of the best score we track. Arena 1441 at $0.1138 per 1M tokens blended at its vendor’s own price.
Best deal at each quality level
The right answer depends on how smart you need it to be — score per dollar on its own always points at the cheapest weak model. These are the best deals inside each capability band.
1 model reach the price/quality frontier only when priced at what you can actually pay: DeepSeek V4 Flash. On list prices alone they look like poor value.
| 1 | Llama 3.2 1B InstructBest value Meta | 1055 | $0.0100 | $0.0100 | — | 105,500 |
| 2 | GPT OSS 20BBest value OpenAI | 1287 | $0.0180 | $0.0180 | — | 71,500 |
| 3 | Llama 3.2 3B Instruct Meta | 1110 | $0.0200 | $0.0200 | — | 55,500 |
| 4 | Llama 3.1 8b Instruct Meta | 1187 | $0.0250 | $0.0250 | — | 47,480 |
| 5 | gemma-3-4b-itBest value Google | 1291 | $0.0500 | $0.0500 | — | 25,820 |
| 6 | Gemma 3 4B IT (Bedrock)Best value AWS Bedrock | 1291 | $0.0500 | $0.0500 | — | 25,820 |
| 7 | GPT OSS 120BBest value OpenAI | 1365 | $0.0590 | $0.0590 | — | 23,136 |
| 8 | Gemma 3 12B IT Google | 1334 | $0.0625 | $0.0625 | — | 21,344 |
| 9 | Amazon Nova Micro AWS Bedrock | 1268 | $0.0613 | $0.0613 | — | 20,702 |
| 10 | Command R7B Cohere | 1262 | $0.0656 | $0.0656 | — | 19,230 |
| 11 | Phi 4 Microsoft | 1217 | $0.0875 | $0.0875 | — | 13,909 |
| 12 | Gemma 3 27B IT Google | 1358 | $0.1000 | $0.1000 | — | 13,580 |
| 13 | Qwen2.5 Coder 32B Instruct Alibaba | 1230 | $0.0950 | $0.0950 | — | 12,947 |
| 14 | Qwen3.8 27BBest value Alibaba | 1441 | $0.1138 | $0.1138 | — | 12,668 |
| 15 | DeepSeek V4 FlashBest value DeepSeek | 1424 | $0.2625 | $0.1125 at DeepInfra | −57% | 12,658 |
| 16 | Amazon Nova Lite AWS Bedrock | 1298 | $0.1050 | $0.1050 | — | 12,362 |
| 17 | Qwen3 32B Alibaba | 1340 | $1.22 | $0.1300 at DeepInfra | −89% | 10,308 |
| 18 | gpt-oss-20b (Bedrock) AWS Bedrock | 1287 | $0.1275 | $0.1275 | — | 10,094 |
| 19 | Qwen3 30B A3B Alibaba | 1317 | $0.1325 | $0.1325 | — | 9,940 |
| 20 | GPT-5 Nano OpenAI | 1320 | $0.1375 | $0.1375 | — | 9,600 |
| 21 | Google Gemma 3 12B (Bedrock) AWS Bedrock | 1334 | $0.1400 | $0.1400 | — | 9,529 |
| 22 | Step 3.5 Flash StepFun | 1403 | $0.1500 | $0.1500 | — | 9,353 |
| 23 | GLM-4.7-Flash Z.ai (Zhipu AI) | 1351 | $0.1450 | $0.1450 | — | 9,317 |
| 24 | Llama 4 Scout Meta | 1332 | $0.1675 | $0.1500 at OpenRouter | −10% | 8,880 |
| 25 | GLM-4.7-Flash (Bedrock) AWS Bedrock | 1351 | $0.1525 | $0.1525 | — | 8,859 |
| 26 | Llama 4 Scout 17B 16E Instruct Meta | 1279 | $0.1500 | $0.1500 | — | 8,527 |
| 27 | Mistral Small 3.1 24B Instruct Mistral AI | 1277 | $0.1500 | $0.1500 | — | 8,513 |
| 28 | MiMo-V2.6-FlashBest value Xiaomi | 1455 | $0.1750 | $0.1750 | — | 8,314 |
| 29 | MiMo-V2.5 Xiaomi | 1428 | $0.1750 | $0.1750 | — | 8,160 |
| 30 | MiMo-V2-Omni Xiaomi | 1423 | $0.1750 | $0.1750 | — | 8,131 |
| 31 | Qwen3.5 Flash Alibaba | 1397 | $0.1750 | $0.1750 | — | 7,983 |
| 32 | MiMo-V2-Flash Xiaomi | 1395 | $0.1750 | $0.1750 | — | 7,971 |
| 33 | Gemini 2.0 Flash Google | 1354 | $0.1750 | $0.1750 | — | 7,737 |
| 34 | Gemini 2.5 Flash-Lite Google | 1330 | $0.1750 | $0.1750 | — | 7,600 |
| 35 | GPT-4.1 Nano OpenAI | 1300 | $0.1750 | $0.1750 | — | 7,429 |
| 36 | Llama-3.3-70B-Instruct Meta | 1274 | $0.2013 | $0.2013 | — | 6,330 |
| 37 | Hunyuan Hy3 Tencent | 1439 | $0.3500 | $0.2300 at DeepInfra | −34% | 6,257 |
| 38 | GLM-5.3-FlashBest value Z.ai (Zhipu AI) | 1471 | $0.2375 | $0.2375 | — | 6,194 |
| 39 | Qwen3.5 35B-A3B Alibaba | 1394 | $0.6875 | $0.2475 at OpenRouter | −64% | 5,632 |
| 40 | gpt-oss-120b (Bedrock) AWS Bedrock | 1365 | $0.2625 | $0.2625 | — | 5,200 |
| 41 | Google Gemma 3 27B Instruct (Bedrock) AWS Bedrock | 1358 | $0.2675 | $0.2675 | — | 5,077 |
| 42 | Mistral Small 4 Mistral AI | 1325 | $0.2625 | $0.2625 | — | 5,048 |
| 43 | GPT-4o mini OpenAI | 1310 | $0.2625 | $0.2625 | — | 4,990 |
| 44 | DeepSeek V3.2 DeepSeek | 1420 | $0.3150 | $0.2900 at DeepInfra | −8% | 4,897 |
| 45 | Llama 4 Maverick Meta | 1360 | $0.3775 | $0.3043 at OpenRouter | −19% | 4,470 |
| 46 | GLM-4.5-Air Z.ai (Zhipu AI) | 1384 | $0.4250 | $0.3100 at Novita AI | −27% | 4,465 |
| 47 | Command R Cohere | 1163 | $0.2625 | $0.2625 | — | 4,430 |
| 48 | DeepSeek V3.1 DeepSeek | 1417 | $0.3200 | $0.3200 | — | 4,428 |
| 49 | Qwen3-Next 80B-A3B Instruct Alibaba | 1417 | $0.8750 | $0.3425 at DeepInfra | −61% | 4,137 |
| 50 | DeepSeek V3.1 Terminus DeepSeek | 1417 | $0.3625 | $0.3625 | — | 3,909 |
| 51 | Qwen3 VL 235B A22B Instruct Alibaba | 1420 | $0.3700 | $0.3700 | — | 3,838 |
| 52 | MiniMax-M2.7 MiniMax | 1405 | $0.5250 | $0.3675 at OpenRouter | −30% | 3,823 |
| 53 | Qwen Plus Alibaba | 1326 | $0.6000 | $0.3900 at OpenRouter | −35% | 3,400 |
| 54 | MiniMax-M2.5 MiniMax | 1359 | $0.5250 | $0.4000 at DeepInfra | −24% | 3,398 |
| 55 | Qwen3-Next 80B-A3B (Thinking) Alibaba | 1368 | $1.88 | $0.4125 at OpenRouter | −78% | 3,316 |
| 56 | MiniMax M1 MiniMax | 1343 | $0.4125 | $0.4125 | — | 3,256 |
| 57 | GPT-5.6 Luna OpenAI | 1430 | $0.4500 | $0.4500 | — | 3,178 |
| 58 | Llama 3.1 70B Instruct Meta | 1261 | $0.4000 | $0.4000 | — | 3,153 |
| 59 | GLM-4.6V Z.ai (Zhipu AI) | 1377 | $0.4500 | $0.4500 | — | 3,060 |
| 60 | DeepSeek V3 DeepSeek | 1332 | $0.4375 | $0.4375 | — | 3,045 |
| 61 | GPT-5.4 nano OpenAI | 1372 | $0.4625 | $0.4625 | — | 2,966 |
| 62 | MiniMax-M3 MiniMax | 1433 | $0.5250 | $0.4850 at DeepInfra | −8% | 2,955 |
| 63 | Qwq 32B Alibaba | 1162 | $0.4000 | $0.4000 | — | 2,905 |
| 64 | GPT-5.6 Luna (Bedrock) AWS Bedrock | 1430 | $2.25 | $0.4950 at Amazon Bedrock | −78% | 2,889 |
| 65 | GPT-5.6 Luna (India) (Bedrock) AWS Bedrock | 1430 | $0.4950 | $0.4950 | — | 2,889 |
| 66 | MiMo-V2.6-ProBest value Xiaomi | 1492 | $0.5437 | $0.5400 at DeepInfra | −1% | 2,763 |
| 67 | MiMo-V2.5-Pro Xiaomi | 1465 | $0.5437 | $0.5437 | — | 2,694 |
| 68 | DeepSeek V4 Pro DeepSeek | 1445 | $0.9900 | $0.5437 at NVIDIA | −45% | 2,657 |
| 69 | MiniMax-M2.1 MiniMax | 1392 | $0.5250 | $0.5250 | — | 2,651 |
| 70 | MiniMax M2.1 (Bedrock) AWS Bedrock | 1392 | $0.5250 | $0.5250 | — | 2,651 |
| 71 | MiMo-V2-Pro Xiaomi | 1436 | $0.5437 | $0.5437 | — | 2,641 |
| 72 | Qwen3.7 Plus Alibaba | 1455 | $0.7000 | $0.5600 at OpenRouter | −20% | 2,598 |
| 73 | MiniMax M2.5 (Bedrock) AWS Bedrock | 1359 | $0.5250 | $0.5250 | — | 2,589 |
| 74 | Devstral 2 Mistral AI | 1340 | $0.5250 | $0.5250 | — | 2,552 |
| 75 | MiniMax-M2 MiniMax | 1340 | $0.5250 | $0.5250 | — | 2,552 |
| 76 | MiniMax M2 (Bedrock) AWS Bedrock | 1340 | $0.5250 | $0.5250 | — | 2,552 |
| 77 | Gemini 3.1 Flash Lite Google | 1416 | $0.5625 | $0.5625 | — | 2,517 |
| 78 | Llama 3.3 70B Meta | 1315 | $0.6000 | $0.6000 | — | 2,192 |
| 79 | GPT-5 Mini OpenAI | 1373 | $0.6875 | $0.6875 | — | 1,997 |
| 80 | Qwen3.5 122B-A10B Alibaba | 1417 | $1.10 | $0.7150 at OpenRouter | −35% | 1,982 |
| 81 | Qwen3.6 Plus Alibaba | 1437 | $1.13 | $0.7312 at OpenRouter | −35% | 1,965 |
| 82 | GLM-4.7 Z.ai (Zhipu AI) | 1435 | $1.00 | $0.7375 at DeepInfra | −26% | 1,946 |
| 83 | GPT-4.1 Mini OpenAI | 1345 | $0.7000 | $0.7000 | — | 1,921 |
| 84 | Mistral Large 3 Mistral AI | 1428 | $0.7500 | $0.7500 | — | 1,904 |
| 85 | DeepSeek R1 DeepSeek | 1373 | $0.7250 | $0.7250 | — | 1,894 |
| 86 | Qwen3.5 27B Alibaba | 1409 | $0.8250 | $0.8250 | — | 1,708 |
| 87 | Mistral Medium 3.1 Mistral AI | 1350 | $0.8000 | $0.8000 | — | 1,688 |
| 88 | Gemini 3.5 Flash Lite Google | 1435 | $0.8500 | $0.8500 | — | 1,688 |
| 89 | Gemini 2.5 Flash Google | 1417 | $0.8500 | $0.8500 | — | 1,667 |
| 90 | GLM-4.6 Z.ai (Zhipu AI) | 1440 | $1.00 | $0.8750 at DeepInfra | −13% | 1,646 |
| 91 | Kimi K2.5 Moonshot AI | 1445 | $1.20 | $0.9000 at DeepInfra | −25% | 1,606 |
| 92 | Gemini 3 Flash Google | 1442 | $0.9000 | $0.9000 | — | 1,602 |
| 93 | GLM-5 Z.ai (Zhipu AI) | 1446 | $1.55 | $0.9300 at OpenRouter | −40% | 1,555 |
| 94 | Qwen3 VL 235B A22B Thinking Alibaba | 1400 | $0.9320 | $0.9320 | — | 1,502 |
| 95 | Kimi K2 Moonshot AI | 1371 | $0.9250 | $0.9250 | — | 1,482 |
| 96 | GLM-4.5V Z.ai (Zhipu AI) | 1332 | $0.9000 | $0.9000 | — | 1,480 |
| 97 | GPT-3.5-turbo OpenAI | 1094 | $0.7500 | $0.7500 | — | 1,459 |
| 98 | GLM-4.7 (Bedrock) AWS Bedrock | 1435 | $1.00 | $1.00 | — | 1,435 |
| 99 | GLM-4.5 Z.ai (Zhipu AI) | 1430 | $1.00 | $1.00 | — | 1,430 |
| 100 | Mistral Large 4 Mistral AI | 1427 | $1.03 | $1.03 | — | 1,382 |
| 101 | Qwen3.5 397B-A17B Alibaba | 1438 | $1.35 | $1.09 at DeepInfra | −19% | 1,322 |
| 102 | Qwen/Qwen3-VL-235B-A22B-Instruct (Bedrock) AWS Bedrock | 1401 | $1.06 | $1.06 | — | 1,319 |
| 103 | Kimi K2 Thinking Moonshot AI | 1371 | $1.08 | $1.08 | — | 1,275 |
| 104 | Kimi K2 Thinking (Bedrock) AWS Bedrock | 1371 | $1.08 | $1.08 | — | 1,275 |
| 105 | GLM-5.2 Z.ai (Zhipu AI) | 1463 | $2.15 | $1.16 at DeepInfra | −46% | 1,258 |
| 106 | Kimi K2.5 (Bedrock) AWS Bedrock | 1445 | $1.20 | $1.20 | — | 1,204 |
| 107 | Qwen3-VL 235B-A22B Alibaba | 1401 | $1.22 | $1.22 | — | 1,144 |
| 108 | Qwen3 235B-A22B Alibaba | 1366 | $1.22 | $1.22 | — | 1,115 |
| 109 | Kimi K2.6 Moonshot AI | 1455 | $1.71 | $1.34 at OpenRouter | −22% | 1,086 |
| 110 | Gemini 3.8 FlashBest value Google | 1499 | $1.50 | $1.50 | — | 999 |
| 111 | Gemini 3.7 Flash Google | 1486 | $1.50 | $1.50 | — | 991 |
| 112 | Gemini 3.6 Flash Google | 1479 | $1.50 | $1.50 | — | 986 |
| 113 | GLM-5.1 Z.ai (Zhipu AI) | 1461 | $2.15 | $1.48 at OpenRouter | −31% | 985 |
| 114 | Amazon Nova Pro AWS Bedrock | 1348 | $1.40 | $1.40 | — | 963 |
| 115 | GLM-5 (Bedrock) AWS Bedrock | 1446 | $1.55 | $1.55 | — | 933 |
| 116 | Grok 4.3 xAI | 1397 | $1.56 | $1.56 | — | 894 |
| 117 | GPT-5.4 mini OpenAI | 1411 | $1.69 | $1.69 | — | 836 |
| 118 | Qwen3.7 Max Alibaba | 1476 | $3.75 | $1.88 at Novita AI | −50% | 787 |
| 119 | Claude 3.5 Haiku Anthropic | 1255 | $1.60 | $1.60 | — | 784 |
| 120 | o3 Mini High OpenAI | 1337 | $1.74 | $1.74 | — | 767 |
| 121 | GLM-5V-Turbo Z.ai (Zhipu AI) | 1437 | $1.90 | $1.90 | — | 756 |
| 122 | Muse Spark 1.2 Meta | 1482 | $2.00 | $2.00 | — | 741 |
| 123 | Muse Spark 1.1 Meta | 1479 | $2.00 | $2.00 | — | 740 |
| 124 | o4-mini OpenAI | 1382 | $1.93 | $1.93 | — | 718 |
| 125 | Claude Haiku 4.5 Anthropic | 1396 | $2.00 | $2.00 | — | 698 |
| 126 | o3-mini OpenAI | 1319 | $1.93 | $1.93 | — | 685 |
| 127 | Qwen3 Max Alibaba | 1439 | $2.40 | $2.40 | — | 600 |
| 128 | Qwen3.8 Max Alibaba | 1483 | $3.00 | $2.48 at DeepInfra | −17% | 599 |
| 129 | Qwen2.5 72B Instruct Alibaba | 1269 | $2.45 | $2.45 | — | 518 |
| 130 | Kimi K2 Thinking Turbo Moonshot AI | 1414 | $2.86 | $2.86 | — | 494 |
| 131 | Grok 4.5 xAI | 1448 | $3.00 | $3.00 | — | 483 |
| 132 | Kimi K3 Moonshot AI | 1473 | $6.00 | $3.05 at OpenRouter | −49% | 483 |
| 133 | Grok 4.6 xAI | 1428 | $3.00 | $3.00 | — | 476 |
| 134 | mistral-medium-3-5 Mistral AI | 1421 | $3.00 | $3.00 | — | 474 |
| 135 | Grok 4.7 xAI | 1399 | $3.00 | $3.00 | — | 466 |
| 136 | Qwen Max Alibaba | 1282 | $2.80 | $2.80 | — | 458 |
| 137 | Qwen3-Coder 480B-A35B Instruct Alibaba | 1357 | $3.00 | $3.00 | — | 452 |
| 138 | Gemini 3.5 Flash Google | 1477 | $3.38 | $3.38 | — | 438 |
| 139 | Gemini 2.5 Pro Google | 1458 | $3.44 | $3.44 | — | 424 |
| 140 | GPT-5.1 OpenAI | 1422 | $3.44 | $3.44 | — | 414 |
| 141 | GPT-5 OpenAI | 1406 | $3.44 | $3.44 | — | 409 |
| 142 | o3 OpenAI | 1422 | $3.50 | $3.50 | — | 406 |
| 143 | GPT-4.1 OpenAI | 1372 | $3.50 | $3.50 | — | 392 |
| 144 | Mistral Large Mistral AI | 1176 | $3.00 | $3.00 | — | 392 |
| 145 | Claude Sonnet 5.5 Anthropic | 1471 | $4.00 | $4.00 | — | 368 |
| 146 | Claude Sonnet 5.5 (Bedrock) AWS Bedrock | 1471 | $4.00 | $4.00 | — | 368 |
| 147 | GPT-5.6 Sol OpenAI | 1457 | $8.00 | $4.00 at OpenRouter | −50% | 364 |
| 148 | Claude Sonnet 5 Anthropic | 1442 | $4.00 | $4.00 | — | 361 |
| 149 | Claude Sonnet 5 (Bedrock) AWS Bedrock | 1442 | $4.00 | $4.00 | — | 361 |
| 150 | Gemini 3.1 Pro Preview Google | 1481 | $4.50 | $4.50 | — | 329 |
| 151 | Claude Sonnet 5 (India) (Bedrock) AWS Bedrock | 1442 | $4.40 | $4.40 | — | 328 |
| 152 | GPT-5.6 Terra OpenAI | 1447 | $4.50 | $4.50 | — | 322 |
| 153 | Command A Cohere | 1365 | $4.38 | $4.38 | — | 312 |
| 154 | GPT-4o OpenAI | 1355 | $4.38 | $4.38 | — | 310 |
| 155 | GPT-5.2 OpenAI | 1412 | $4.81 | $4.81 | — | 293 |
| 156 | GPT-5.6 Terra (Bedrock) AWS Bedrock | 1447 | $5.63 | $4.95 at Amazon Bedrock | −12% | 292 |
| 157 | GPT-5.6 Terra (India) (Bedrock) AWS Bedrock | 1447 | $4.95 | $4.95 | — | 292 |
| 158 | Amazon Nova Premier AWS Bedrock | 1400 | $5.00 | $5.00 | — | 280 |
| 159 | Command R+ Cohere | 1204 | $4.38 | $4.38 | — | 275 |
| 160 | GPT-5.4 OpenAI | 1452 | $5.63 | $5.63 | — | 258 |
| 161 | Claude 4 Sonnet Anthropic | 1339 | $5.20 | $5.20 | — | 258 |
| 162 | Claude Sonnet 4.6 Anthropic | 1458 | $6.00 | $6.00 | — | 243 |
| 163 | Claude Sonnet 4.5 (latest) Anthropic | 1439 | $6.00 | $6.00 | — | 240 |
| 164 | GPT-5.4 (Bedrock) AWS Bedrock | 1452 | $6.19 | $6.19 | — | 235 |
| 165 | Grok 4 xAI | 1411 | $6.00 | $6.00 | — | 235 |
| 166 | Kimi K3 (Bedrock) AWS Bedrock | 1473 | $6.60 | $6.60 | — | 223 |
| 167 | Anthropic Claude Sonnet 4.6 (Bedrock) AWS Bedrock | 1458 | $6.60 | $6.60 | — | 221 |
| 168 | Claude Opus 5.5Best value Anthropic | 1515 | $8.00 | $8.00 | — | 189 |
| 169 | Claude Opus 5.5 (Bedrock)Best value AWS Bedrock | 1515 | $8.00 | $8.00 | — | 189 |
| 170 | GPT-5.6 Sol (Bedrock) AWS Bedrock | 1457 | $11.25 | $8.80 at Amazon Bedrock | −22% | 166 |
| 171 | Step 2 (16K) StepFun | 1321 | $8.02 | $8.02 | — | 165 |
| 172 | Claude Opus 4.6 Anthropic | 1498 | $10.00 | $10.00 | — | 150 |
| 173 | Claude Opus 5 Anthropic | 1503 | $10.00 | $10.00 | — | 150 |
| 174 | Claude Opus 5 (Bedrock) AWS Bedrock | 1503 | $11.00 | $10.00 at Amazon Bedrock | −9% | 150 |
| 175 | Claude Opus 4.7 Anthropic | 1483 | $10.00 | $10.00 | — | 148 |
| 176 | Claude Opus 4.7 (Bedrock) AWS Bedrock | 1483 | $10.00 | $10.00 | — | 148 |
| 177 | Claude Opus 4.8 Anthropic | 1454 | $10.00 | $10.00 | — | 145 |
| 178 | Claude Opus 4.8 (Bedrock) AWS Bedrock | 1454 | $10.00 | $10.00 | — | 145 |
| 179 | Claude Opus 4.5 (latest) Anthropic | 1451 | $10.00 | $10.00 | — | 145 |
| 180 | Claude Opus 5 (India) (Bedrock) AWS Bedrock | 1503 | $11.00 | $11.00 | — | 137 |
| 181 | GPT-5.5 OpenAI | 1467 | $11.25 | $11.25 | — | 130 |
| 182 | GPT-5.5 (Bedrock) AWS Bedrock | 1467 | $12.38 | $12.38 | — | 119 |
| 183 | Claude Fable 5 Anthropic | 1491 | $20.00 | $20.00 | — | 75 |
| 184 | Claude Fable 5 (Bedrock) AWS Bedrock | 1491 | $20.00 | $20.00 | — | 75 |
| 185 | Claude Opus 4 Anthropic | 1366 | $25.75 | $25.75 | — | 53 |
| 186 | o1 OpenAI | 1353 | $26.25 | $26.25 | — | 52 |
| 187 | Claude Opus 4.1 (latest) Anthropic | 1419 | $30.00 | $30.00 | — | 47 |
| 188 | GPT-4 OpenAI | 1186 | $37.50 | $37.50 | — | 32 |
Best prices are third-party listings via models.dev, restricted to first-party vendors, the major clouds and established inference hosts — not rates we verify with each provider the way we verify first-party pricing. Cheaper obscure resellers exist in the data and are shown on each model page, but we will not rank on them. Use this as a shortlist to check: confirm quantisation, context limit, rate limits and data policy before switching, because a cheaper host is not always serving the same thing. Blended price weights input and output 3:1.
Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 12 October 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.
FAQ
What does “best value” mean here?
Arena score divided by price per 1M tokens, blended 3:1 input to output — but priced at the cheapest major provider selling that model, not at the model vendor's list price. A model is also flagged “Best value” when it sits on the price/quality frontier: nothing we track is both smarter and cheaper.
Why is this different from other value rankings?
Everyone else divides quality by the lab's list price. That answers whether a vendor's own price is fair, not what the most intelligence per dollar is. The same open-weight model is often resold 10–25× cheaper, so ranking on list price systematically undervalues models with a competitive hosting market.
Are these cheaper prices trustworthy?
They are third-party listings collected from models.dev, not rates we verify with each host the way we verify first-party pricing. We only quote first-party vendors, the major clouds and established inference hosts — the feed contains cheaper obscure resellers, and we deliberately do not rank on those, though you can see them on each model page. Treat the table as a shortlist to check: confirm quantisation, context limit, rate limits and data policy before switching, because a cheaper host is not always serving the same thing.
How often is it updated?
The site rebuilds daily against live pricing, so both the list prices and the third-party listings refresh every day, and the ranking moves with them.
Related
- Intelligence per dollar at list prices — the same leaderboard priced the conventional way.
- Which model should I use? — set a quality bar and get the cheapest model that clears it.
- Endpoint price dataset (JSON, CC BY 4.0) — every provider offering behind this ranking.
- Methodology — how scores, blended price and the frontier are computed.
Estimates for planning only. Verify current pricing with each provider. Data rebuilt daily · https://aicalculatorpro.com/best-value-llm/