Score vs. cost per question
MoonshotAI models in color, every other model in grey
Provider
2 models tested, compared with 76 models from other labs.
MoonshotAI#9Kimi K3.1 Pro77.5% verification score38 tok/s1.3 s first token$0.01 / questionMoonshotAI#33Kimi K2.7 Code65.0% verification score136 tok/s0.4 s first token$0.006 / questionMoonshotAI models in color, every other model in grey
MoonshotAI models in color, every other model in grey
MoonshotAI models highlighted against every model in this run · higher is better
MoonshotAI models highlighted against every model in this run · higher is better
MoonshotAI models highlighted against every model in this run · lower is better
MoonshotAI models highlighted against every model in this run · lower is better
MoonshotAI models highlighted against every model in this run · lower is better
MoonshotAI models highlighted against every model in this run · higher is better
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | Kimi K3.1 Pro MoonshotAI · served by Moonshot AI | 77.5 | 62 / 80 | 38 | 1.3 s | $0.01 | $2 / $10 | 1M |
| 2 | Kimi K2.7 Code MoonshotAI · served by Inceptron | 65.0 | 52 / 80 | 136 | 0.4 s | $0.006 | $0.56 / $3.1 | 262k |