View overall rankings across AI models on front-end web development tasks, including agentic coding workflows that require multi-step reasoning and tool use.
| Rank Spread | ||||||
|---|---|---|---|---|---|---|
| 1 | 11 | Anthropic · Proprietary | 1765+23/-23 | 1,106 | $10 / $50 | 1M |
| 2 | 25 | Alibaba · Proprietary | 1688+18/-18 | 1,472 | $2 / $6 | N/A |
| 3 | 25 | Anthropic · Proprietary | 1687+8/-8 | 10,583 | $5 / $25 | 1M |
| 4 | 26 | Moonshot · Kimi K3 license | 1674+11/-11 | 4,544 | $3 / $15 | 1M |
| 5 | 26 | Alibaba · Proprietary | 1669+12/-12 | 3,222 | $2 / $6 | 1M |
| 6 | 46 | Anthropic · Proprietary | 1661+7/-7 | 10,530 | $5 / $25 | 1M |
| 7 | 713 | SpaceXAI · Proprietary | 1629+17/-17 | 1,534 | $2 / $6 | 500K |
| 8 | 712 | Anthropic · Proprietary | 1628+8/-8 | 9,159 | $10 / $50 | 1M |
| 9 | 713 | Tencent · Apache 2.0 | 1626+17/-17 | 1,472 | $0.83 / $2.50 | 1M |
| 10 | 714 | Alibaba · qwen-community-1.0 | 1622+15/-15 | 1,977 | $0.16 / $0.47 | 1M |
| 11 | 713 | OpenAI · Proprietary | 1616+7/-7 | 10,813 | $4 / $20 | 1.1M |
| 12 | 715 | Z.ai · MIT | 1609+13/-13 | 2,745 | $1.40 / $4.40 | 1M |
| 13 | 818 | Z.ai · MIT | 1604+16/-16 | 1,781 | $0.15 / $0.50 | 1M |
| 14 | 1118 | Alibaba · Apache 2.0 | 1597+11/-11 | 3,349 | $0.40 / $3 | N/A |
| 15 | 1219 | Google · Proprietary | 1587+12/-12 | 3,007 | $0.75 / $3.75 | 1M |
| 16 | 1319 | Z.ai · MIT | 1585+7/-7 | 9,660 | $1.40 / $4.40 | 1M |
| 17 | 1319 | DeepSeek · MIT | 1582+11/-11 | 3,375 | $1.32 / $3.96 | N/A |
| 18 | 1319 | DeepSeek · MIT | 1581+10/-10 | 4,017 | $0.44 / $1.32 | 1M |
| 19 | 1523 | Google · Proprietary | 1567+12/-12 | 2,728 | $0.75 / $3.75 | 1M |
| 20 | 1923 | Anthropic · Proprietary | 1563+7/-7 | 12,721 | $5 / $25 | 1M |
| 21 | 1924 | Anthropic · Proprietary | 1557+6/-6 | 15,534 | $5 / $25 | 1M |
| 22 | 1924 | Anthropic · Proprietary | 1557+6/-6 | 16,003 | $5 / $25 | 1M |
| 23 | 1925 | SpaceXAI · Proprietary | 1556+8/-8 | 7,208 | $2 / $6 | 500K |
| 24 | 2130 | Anthropic · Proprietary | 1546+6/-6 | 17,987 | $5 / $25 | 1M |
| 25 | 2430 | Meta · Proprietary | 1540+8/-8 | 7,184 | $1.25 / $4.25 | N/A |
| 26 | 2430 | Anthropic · Proprietary | 1540+7/-7 | 11,648 | $5 / $25 | 1M |
| 27 | 2430 | Google · Proprietary | 1538+8/-8 | 7,860 | $0.75 / $3.75 | 1M |
| 28 | 2431 | Anthropic · Proprietary | 1537+8/-8 | 8,219 | $2 / $10 | 1M |
| 29 | 2430 | Anthropic · Proprietary | 1536+6/-6 | 19,154 | $5 / $25 | 1M |
| 30 | 2336 | Meta · Proprietary | 1534+14/-14 | 2,065 | $1.25 / $4.25 | N/A |
| 31 | 3036 | Anthropic · Proprietary | 1522+5/-5 | 21,266 | $1.50 / $7.50 | 1M |
| 32 | 2939 | Bytedance · Proprietary | 1522+8/-8 | 8,469 | N/A | N/A |
| 33 | 3039 | OpenAI · Proprietary | 1519+8/-8 | 6,736 | $0.20 / $1.20 | 1M |
| 34 | 3039 | OpenAI · Proprietary | 1519+8/-8 | 6,654 | $2 / $12 | 1M |
| 35 | 3039 | Alibaba · Proprietary | 1517+8/-8 | 8,371 | $1.48 / $4.42 | 1M |
| 36 | 3041 | Tencent · Apache 2.0 | 1511+11/-11 | 3,125 | $0.08 / $0.33 | 262.1K |
| 37 | 3240 | OpenAI · Proprietary | 1509+6/-6 | 14,606 | $5 / $30 | N/A |
| 38 | 3241 | Moonshot · Modified MIT | 1509+7/-7 | 9,589 | $0.95 / $4 | 262.1K |
| 39 | 3241 | Z.ai · MIT | 1508+7/-7 | 9,959 | $1.40 / $4.40 | 202.8K |
| 40 | 3643 | Google · Proprietary | 1501+8/-8 | 8,537 | $0.75 / $4.50 | 1M |
| 41 | 3746 | Anthropic · Proprietary | 1495+8/-8 | 10,595 | $5 / $25 | 200K |
| 42 | 4046 | Google · Proprietary | 1492+7/-7 | 11,046 | $0.75 / $4.50 | 1M |
| 43 | 4049 | MiniMax · MiniMax Community License | 1487+7/-7 | 11,631 | $0.30 / $1.20 | 524.3K |
| 44 | 4149 | OpenAI · Proprietary | 1486+6/-6 | 16,595 | $5 / $30 | N/A |
| 45 | 4151 | Alibaba · Proprietary | 1479+13/-13 | 2,602 | $1.03 / $6.16 | 262.1K |
| 46 | 4351 | Xiaomi · MIT | 1475+6/-6 | 14,911 | $0.43 / $0.87 | 1.1M |
| 47 | 4353 | Moonshot · Modified MIT | 1473+10/-10 | 4,682 | $0.66 / $3.40 | 262.1K |
| 48 | 4554 | Anthropic · Proprietary | 1468+7/-7 | 12,903 | $5 / $25 | 200K |
| 49 | 4554 | DeepSeek · MIT | 1464+7/-7 | 12,404 | $1.32 / $3.96 | 1M |
| 50 | 4361 | OpenAI · Proprietary | 1463+19/-19 | 1,277 | $2.50 / $15 | 1.1M |
| 51 | 4754 | Alibaba · Proprietary | 1460+6/-6 | 17,251 | $0.33 / $1.95 | 1M |
| 52 | 4755 | OpenAI · Proprietary | 1457+6/-6 | 14,652 | $5 / $30 | N/A |
| 53 | 4171 | Google · Proprietary | 1449+42/-42 | 228 | $0.15 / $1.25 | 1M |
| 54 | 5263 | Google · Proprietary | 1446+5/-5 | 22,517 | $1 / $6 | 1M |
| 55 | 5164 | DeepSeek · MIT | 1446+7/-7 | 13,185 | $1.32 / $3.96 | 1M |
| 56 | 4866 | OpenAI · Proprietary | 1442+19/-19 | 1,316 | $2.50 / $15 | 1.1M |
| 57 | 5266 | Google · Proprietary | 1438+9/-9 | 13,578 | $2 / $12 | 1M |
| 58 | 5266 | Xiaomi · MIT | 1438+6/-6 | 13,809 | $0.14 / $0.28 | 1.1M |
| 59 | 5266 | Google · Proprietary | 1438+9/-9 | 10,458 | $0.50 / $3 | 1M |
| 60 | 5366 | Moonshot · Modified MIT | 1436+5/-5 | 19,055 | $0.60 / $3 | N/A |
| 61 | 5266 | Z.ai · MIT | 1436+8/-8 | 7,060 | $1 / $3.20 | 202.8K |
| 62 | 5267 | Z.ai · MIT | 1434+12/-12 | 3,811 | $0.40 / $1.75 | 204.8K |
| 63 | 5366 | Xiaomi · Proprietary | 1433+8/-8 | 6,960 | $1 / $3 | 1M |
| 64 | 5566 | DeepSeek · MIT | 1431+7/-7 | 9,493 | $0.44 / $1.32 | 1M |
| 65 | 5575 | OpenAI · Proprietary | 1419+16/-16 | 3,034 | $1.25 / $10 | 400K |
| 66 | 5479 | OpenAI · Proprietary | 1416+23/-23 | 1,055 | $0.88 / $7 | 400K |
| 67 | 6476 | Thinky · Apache 2.0 | 1408+8/-8 | 7,894 | $1 / $4.05 | 524.3K |
| 68 | 6379 | OpenAI · Proprietary | 1408+14/-14 | 2,514 | $1.75 / $14 | 400K |
| 69 | 6479 | Moonshot · Modified MIT | 1405+12/-12 | 3,097 | $0.45 / $2.25 | 262.1K |
| 70 | 6479 | Thinky · Apache 2.0 | 1405+10/-10 | 4,714 | $0.50 / $1.20 | 524.3K |
| 71 | 6483 | Z.ai · Proprietary | 1400+14/-14 | 2,185 | $1.20 / $4 | 202.8K |
| 72 | 6580 | MiniMax · Modified MIT | 1398+6/-6 | 14,930 | $0.30 / $1.20 | 204.8K |
| 73 | 6579 | Alibaba · Apache 2.0 | 1398+5/-5 | 19,563 | $0.39 / $2.34 | 262.1K |
| 74 | 6581 | OpenAI · Proprietary | 1397+7/-7 | 11,278 | $0.75 / $4.50 | 400K |
| 75 | 6783 | Anthropic · Proprietary | 1392+8/-8 | 12,772 | $3 / $15 | 200K |
| 76 | 6585 | OpenAI · Proprietary | 1391+12/-12 | 4,754 | $0.63 / $5 | 400K |
| 77 | 6786 | Anthropic · Proprietary | 1389+11/-11 | 6,773 | $15 / $75 | 200K |
| 78 | 6687 | OpenAI · Proprietary | 1388+13/-13 | 2,221 | $2.50 / $15 | 1.1M |
| 79 | 6786 | MiniMax · MIT | 1387+10/-10 | 7,285 | $0.30 / $1.20 | 204.8K |
| 80 | 7286 | Anthropic · Proprietary | 1385+7/-7 | 15,152 | $3 / $15 | 200K |
| 81 | 7387 | MiniMax · Modified MIT | 1384+8/-8 | 7,197 | $0.27 / $1.08 | 204.8K |
| 82 | 7486 | Google · Proprietary | 1383+5/-5 | 20,909 | $0.50 / $3 | 1M |
| 83 | 7690 | SpaceXAI · Proprietary | 1374+6/-6 | 14,575 | $1.25 / $2.50 | 1M |
| 84 | 7494 | Upstage · Proprietary | 1371+17/-17 | 1,404 | $0.03 / $0.12 | 524.3K |
| 85 | 7693 | OpenAI · Proprietary | 1370+12/-12 | 3,493 | $1.75 / $14 | 400K |
| 86 | 8394 | Google · Apache 2.0 | 1363+7/-7 | 9,470 | $0.99 / $1.49 | 131.1K |
| 87 | 7798 | Google · Apache 2.0 | 1361+17/-17 | 1,442 | N/A | N/A |
| 88 | 8395 | DeepSeek · MIT | 1361+9/-9 | 6,638 | $0.27 / $0.40 | 163.8K |
| 89 | 8198 | Meta · Apache-2.0 | 1360+16/-16 | 1,511 | N/A | N/A |
| 90 | 8495 | Alibaba · Apache 2.0 | 1358+8/-8 | 7,837 | $0.29 / $2.40 | 262.1K |
| 91 | 8496 |
source & further reading
arena.ai — original article
Audio Realism Benchmark: Measuring Realism in Audio Models
Kimi K3’s Design Secret may be in its Thinking Traces
Thinking Machines’ Open Weights Model is Now on Design Arena