Code Arena🏆Overall
View overall rankings across AI models on agentic coding tasks involving multi-step reasoning and tool use.
Apr 1, 2026
224,709 votes
21 open source models
Rank Spread | |||||||
|---|---|---|---|---|---|---|---|
| 1 | 9 | Z.ai · MIT | 1441+10/-10 | 616 | 4,536 | $1 / $3.20 | 202.8K |
| 2 | 10 | Z.ai · MIT | 1439+10/-10 | 616 | 4,876 | $0.39 / $1.75 | 202.8K |
| 3 | 14 | Moonshot · Modified MIT | 1429+8/-8 | 816 | 6,694 | $0.60 / $3 | N/A |
| 4 | 17 | Moonshot · Modified MIT | 1408+11/-11 | 1526 | 3,610 | $0.38 / $1.72 | 262.1K |
| 5 | 20 | MiniMax · Modified MIT | 1396+8/-8 | 1730 | 6,716 | $0.12 / $0.99 | 196.6K |
| 6 | 22 | MiniMax · MIT | 1391+8/-8 | 1730 | 9,275 | $0.27 / $0.95 | 196.6K |
| 7 | 26 | Alibaba · Apache 2.0 | 1386+9/-9 | 1830 | 5,559 | $0.39 / $2.34 | 262.1K |
| 8 | 31 | DeepSeek · MIT | 1368+8/-8 | 2833 | 8,118 | $0.26 / $0.38 | 163.8K |
| 9 | 32 | Alibaba · Apache 2.0 | 1362+10/-10 | 3034 | 4,272 | $0.26 / $2.08 | 262.1K |
| 10 | 33 | Z.ai · MIT | 1354+9/-9 | 3135 | 8,345 | $0.39 / $1.90 | 204.8K |
| 11 | 34 | Alibaba · Apache 2.0 | 1344+10/-10 | 3240 | 3,958 | $0.20 / $1.56 | 262.1K |
| 12 | 36 | Xiaomi · MIT | 1337+8/-8 | 3440 | 6,737 | $0.09 / $0.29 | 262.1K |
| 13 | 38 | Moonshot · Modified MIT | 1329+6/-6 | 3440 | 15,230 | $1.15 / $8 | 262.1K |
| 14 | 40 | DeepSeek · MIT | 1327+7/-7 | 3440 | 9,603 | $0.26 / $0.38 | 163.8K |
| 15 | 42 | MiniMax · Apache 2.0 | 1303+9/-9 | 4144 | 8,400 | $0.26 / $1 | 196.6K |
| 16 | 43 | Xiaomi · MIT | 1300+14/-14 | 4145 | 2,096 | $0.09 / $0.29 | 262.1K |
| 17 | 44 | DeepSeek · MIT | 1285+11/-11 | 4245 | 4,869 | $0.27 / $0.41 | 163.8K |
| 18 | 45 | Alibaba · Apache 2.0 | 1280+6/-6 | 4345 | 15,380 | $0.40 / $1.60 | 262.1K |
| 19 | 47 | Alibaba · Apache 2.0 | 1247+16/-16 | 4652 | 1,817 | $0.16 / $1.30 | 262.1K |
| 20 | 52 | Mistral · Apache 2.0 | 1221+20/-20 | 4756 | 1,031 | $0.50 / $1.50 | N/A |
| 21 | 55 | Mistral · Modified MIT | 1198+17/-17 | 5256 | 1,585 | N/A | N/A |