Real data comparison
Poolside: Laguna S 2.1 (free) vs Xiaomi: MiMo-V2.5
On price, Poolside: Laguna S 2.1 (free) is cheaper ($0.11 vs $0.18 per 1M). In real production usage, Xiaomi: MiMo-V2.5 is used more (rank #2 vs #17 of 291). Across 9 real task categories where both models have classified traffic, Xiaomi: MiMo-V2.5 handles more of the traffic in 9 of them.
- Poolside: Laguna S 2.1 (free)
- Xiaomi: MiMo-V2.5
Head-to-head by real task
Poolside: Laguna S 2.1 (free) leads 0 of 9 shared task categories by real classified traffic share; Xiaomi: MiMo-V2.5 leads 9. Not a benchmark score - this is what developers actually route to each model for, per OpenRouter's task classification.
| Task | Poolside: Laguna S 2.1 (free) | Xiaomi: MiMo-V2.5 |
|---|---|---|
| Repo Scanning | 2.9% | 18.1% |
| Frontend & UI | 4.6% | 14.7% |
| File I/O | 2.4% | 10.7% |
| DevOps | 4.0% | 11.3% |
| DevOps & Config | 5.6% | 12.0% |
| Debugging | 3.3% | 9.0% |
| SQL & Database | 2.8% | 8.3% |
| Memory Extraction | 3.3% | 8.7% |
| Code Generation | 3.0% | 8.1% |
Usage share over time
- Poolside: Laguna S 2.1 (free)
- Xiaomi: MiMo-V2.5
Frequently asked questions
Poolside: Laguna S 2.1 (free) vs Xiaomi: MiMo-V2.5: which is better quality?
Quality data is unavailable for one or both models.
Poolside: Laguna S 2.1 (free) vs Xiaomi: MiMo-V2.5: which is cheaper?
Poolside: Laguna S 2.1 (free) is cheaper at $0.11/1M vs $0.18/1M.
Poolside: Laguna S 2.1 (free) vs Xiaomi: MiMo-V2.5: which is used more?
Xiaomi: MiMo-V2.5 has higher real OpenRouter usage share (rank #2 vs #17 of 291).
Poolside: Laguna S 2.1 (free) vs Xiaomi: MiMo-V2.5: which wins more real-world task categories?
Xiaomi: MiMo-V2.5 handles more traffic in 9 of 9 shared task categories where both models have classified OpenRouter usage.
Source: OpenRouter (openrouter.ai/rankings), as of August 9, 2026.
Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).
Methodology: smophy.ai/benchmark/methodology
Token counts originate from each provider's own tokenizer and are not directly comparable across providers.