Score vs. cost per question
DeepSeek models in color, every other model in grey
Provider
3 models tested, compared with 75 models from other labs.
DeepSeek models in color, every other model in grey
DeepSeek models in color, every other model in grey
DeepSeek models highlighted against every model in this run · higher is better
DeepSeek models highlighted against every model in this run · higher is better
DeepSeek models highlighted against every model in this run · lower is better
DeepSeek models highlighted against every model in this run · lower is better
DeepSeek models highlighted against every model in this run · lower is better
DeepSeek models highlighted against every model in this run · higher is better
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 DeepSeek · served by Wafer | 73.8 | 59 / 80 | 57 | 0.9 s | $0.00091 | $0.15 / $0.6 | 1M |
| 2 | DeepSeek V4 Flash Vision Exp DeepSeek · served by DeepInfra | 71.2 | 57 / 80 | 170 | 0.7 s | $0.0011 | $0.2156 / $0.6468 | 1M |
| 3 | DeepSeek V4 Pro 0813 DeepSeek · served by Alibaba | 71.2 | 57 / 80 | 56 | 0.8 s | $0.0036 | $1.32 / $3.96 | 1M |