Kimi K3.1 Pro (Venice) vs MiniMax M2.5 (Venice)
On the 4 use cases both models ran, MiniMax M2.5 (Venice) won 3 to 1 (better outcome first, then lower cost).
Pass rate: Kimi K3.1 Pro (Venice) 100% (4 runs) vs MiniMax M2.5 (Venice) 75% (4 runs). Average cost per run: $0.11 vs $0.01.
| Metric | Kimi K3.1 Pro (Venice) | MiniMax M2.5 (Venice) |
|---|---|---|
| Runs on shared use cases | 4 | 4 |
| Pass rate | 100% (4/4) | 75% (3/4) |
| Avg cost per run | $0.11 | $0.01 |
| Avg wall time | 2m | 5m |
| Step-ins per run | 0.00 | 0.00 |
| Use cases won | 1 | 3 |
Use case by use case
- Backtest a moving-average crossover on a bundled synthetic price file: Kimi K3.1 Pro (Venice) better (pass 100% vs 0%)
- Progressive tax on fictional brackets, and pre-tax vs after-tax savings comparison: MiniMax M2.5 (Venice) better (pass 100% vs 100%)
- Read a synthetic annual-report excerpt and compute financial ratios: MiniMax M2.5 (Venice) better (pass 100% vs 100%)
- Work backward from a retirement budget to a savings target, contributions and earliest retirement age: MiniMax M2.5 (Venice) better (pass 100% vs 100%)
Only use cases both models ran are compared; all settings of each model are grouped. How we score.