Leaderboard
DSBench-Hard
1 models scored · metric: score. Prices are the cheapest listed across all serving providers. Pts/$ = score ÷ blended price (3×input + output) / 4 — how much score each dollar buys.
| # | Model | Score | Best in /M | Best out /M | Pts / $ | Context |
|---|---|---|---|---|---|---|
| 🥇 | DeepSeek V4 Flash 0731deepseek | 59.6 | $0.08 | $0.18 | 568 | 1M |
Cheapest scorer: DeepSeek V4 Flash 0731 at $0.08 input /M.