Leaderboard
Artificial Analysis Coding Agent Index
17 models scored · metric: average pass@1. Prices are the cheapest listed across all serving providers. Pts/$ = score ÷ blended price (3×input + output) / 4 — how much score each dollar buys.
Best value · top 5 by pts per dollar
- 1.GPT-5.6 Luna332
- 2.DeepSeek V4 Pro92.1
- 3.Kimi K2.649.3
- 4.GPT-5.6 Terra34.4
- 5.GLM-5.124.5
| # | Model | Score | Best in /M | Best out /M | Pts / $ | Context |
|---|---|---|---|---|---|---|
| 🥇 | GPT-5.6 Solopenai | 80 | $2.50 | $15 | 14.2 | 1.05M |
| 🥈 | GPT-5.6 Terraopenai | 77.4 | $1 | $6 | 34.4 | 1.05M |
| 🥉 | GPT-5.6 Lunaopenai | 74.6 | $0.1 | $0.6 | 332 | 1.05M |
| 4 | Claude Opus 4.7anthropic | 66.6 | $5 | $25 | 6.7 | 1M |
| 5 | GPT-5.5openai | 65.3 | $4.55 | $27.27 | 6.4 | 1.05M |
| 6 | Claude Opus 4.7anthropic | 61.2 | $5 | $25 | 6.1 | 1M |
| 7 | GPT-5.5openai | 60.4 | $4.55 | $27.27 | 5.9 | 1.05M |
| 8 | Claude Opus 4.7anthropic | 59.9 | $5 | $25 | 6.0 | 1M |
| 9 | GPT-5.5openai | 57.8 | $4.55 | $27.27 | 5.7 | 1.05M |
| 10 | GPT-5.4openai | 53.6 | $2.20 | $14 | 10.4 | 1.05M |
| 11 | GLM-5.1zhipuai | 52.7 | $1.40 | $4.40 | 24.5 | 200K |
| 12 | GPT-5.4openai | 52.2 | $2.20 | $14 | 10.1 | 1.05M |
| 13 | Claude Opus 4.6anthropic | 51.3 | $5 | $25 | 5.1 | 1M |
| 14 | Kimi K2.6moonshotai | 50.5 | $0.5 | $2.60 | 49.3 | 262K |
| 15 | DeepSeek V4 Prodeepseek | 50.1 | $0.435 | $0.87 | 92.1 | 1M |
| 16 | Claude Sonnet 4.6anthropic | 49.4 | $3 | $15 | 8.2 | 1M |
| 17 | Gemini 3.1 Pro Previewgoogle | 43 | $2 | $12 | 9.6 | 1.05M |
Cheapest scorer: GPT-5.6 Luna at $0.1 input /M.