Design Arena · Spreadsheet
Head-to-head Elo from Design Arena votes in the Spreadsheet category.
Published by Design Arena- 22
- Models scored
- 1414
- Top score
- 1110
- Median
Distribution of scores
9211414
Leaderboard
22 models
| # | Model | Score | Win rate | Context | Input $ | Output $ |
|---|---|---|---|---|---|---|
| 1 |  Claude Fable 5.1Anthropic | 1414 | 70.4% | 1M | $10.00 | $50.00 |
| 2 | Claude Opus 5.5Anthropic | 1392 | 69.3% | 1M | $4.00 | $20.00 |
| 3 |  GLM-5.1Zhipu AI | 1315 | 72.4% | 200K | $0.90 | $3.59 |
| 4 | Claude Sonnet 5.5Anthropic | 1287 | 53.3% | 1M | $2.00 | $10.00 |
| 5 |  GPT-6.1 SolOpenAI | 1284 | 52.5% | 1.05M | $2.00 | $10.00 |
| 6 |  DeepSeek V4.1 Flash 1017DeepSeek | 1278 | 51.2% | 1.05M | $0.15 | $0.60 |
| 7 |  Kimi K2.6Moonshot AI | 1276 | 54.8% | 262K | $0.95 | $4.00 |
| 8 | Claude Opus 4.8Anthropic | 1240 | 68.0% | 1M | $5.00 | $25.00 |
| 9 |  Gemini 4 ArgonGoogle | 1189 | 32.8% | 1.05M | $2.00 | $10.00 |
| 10 | Claude Opus 5Anthropic | 1158 | 52.4% | 1M | $5.00 | $25.00 |
| 11 | Kimi K3Moonshot AI | 1114 | 32.4% | 1.05M | $3.00 | $15.00 |
| 12 | Gemini 3.7 FlashGoogle | 1110 | 46.9% | 1.05M | $0.75 | $3.75 |
| 13 | Claude Sonnet 5Anthropic | 1097 | 47.1% | 1M | $2.00 | $10.00 |
| 14 |  Muse Spark 1.3Meta | 1092 | 29.9% | 1.05M | $1.25 | $4.25 |
| 15 |  Grok 4.5xAI | 1083 | 45.0% | 500K | $2.00 | $6.00 |
| 16 | Gemini 3.6 FlashGoogle | 1079 | 45.6% | 1.05M | $0.75 | $3.75 |
| 17 | Muse Spark 1.2Meta | 1077 | 45.0% | 1.05M | $1.25 | $4.25 |
| 18 | Gemini 3.5 FlashGoogle | 1077 | 43.5% | 1.05M | $1.50 | $9.00 |
| 19 | Gemini 3.8 FlashGoogle | 1051 | 40.5% | 1.05M | $0.75 | $3.75 |
| 20 |  MiniMax-M3MiniMax | 1051 | 46.1% | 1M | $0.30 | $1.20 |
| 21 | Muse Spark 1.1Meta | 1034 | 35.3% | 1.05M | $1.25 | $4.25 |
| 22 | Grok 4.3xAI | 921 | 34.5% | 1M | $1.25 | $2.50 |