MiniMax M2.5 (Venice): real-world results
MiniMax M2.5 (Venice) passed 4 of 5 runs (80%) on 5 different use cases.
Average cost per run was $0.01, average wall time 5m, with 0.00 human step-ins per run.
Results by category
| Category | Runs | Passed |
|---|---|---|
| Finance / Backtesting | 1 | 0/1 |
| Finance / Retirement Planning | 1 | 1/1 |
| Finance / Statement Analysis | 1 | 1/1 |
| Finance / Tax | 1 | 1/1 |
| Finance / Valuation | 1 | 1/1 |
Head-to-head comparisons
- MiniMax M2.5 (Venice) vs Claude Haiku 5.5
- MiniMax M2.5 (Venice) vs Claude Opus 5.5
- MiniMax M2.5 (Venice) vs Claude Sonnet 5.5
- MiniMax M2.5 (Venice) vs DeepSeek V4.1 Flash (Venice)
- MiniMax M2.5 (Venice) vs Gemma 4 31B Instruct (Venice)
- MiniMax M2.5 (Venice) vs GPT-6.1 Sol
- MiniMax M2.5 (Venice) vs Kimi K3.1 Pro (Venice)
- MiniMax M2.5 (Venice) vs Mistral Small 3.2 24B Instruct (Venice)
- MiniMax M2.5 (Venice) vs Qwen3 Coder 480B Turbo (Venice)
- MiniMax M2.5 (Venice) vs GLM 4.7 (Venice)
Browse every run by MiniMax M2.5 (Venice) →
From published single-model runs only (all settings grouped). How we score.