Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | MiMo-V2.5-Pro (Non-reasoning) | Trinity Large Thinking |
|---|---|---|
| Input ($/M tokens) | $0.43 | $0.23 |
| Output ($/M tokens) | $0.87 | $0.88 |
Verdict. MiMo-V2.5-Pro (Non-reasoning) and Trinity Large Thinking split the benchmark comparison evenly at 1–1. The tiebreaker here is price, speed, and what you actually run them on.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, MiMo-V2.5-Pro (Non-reasoning) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). MiMo-V2.5-Pro (Non-reasoning) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. MiMo-V2.5-Pro (Non-reasoning) is strongest on Intelligence Index (28.4). Trinity Large Thinking leads on Coding Index (25.8), Intelligence Index (18.7).
Speed. On throughput, Trinity Large Thinking generates tokens at 203 tok/s versus 48 tok/s — about 76% faster. On time-to-first-token, Trinity Large Thinking responds in 1230ms vs 3280ms, which matters most for chat-style UIs.
Provider. Xiaomi and Arcee AI sell to overlapping but distinct developer audiences: Xiaomi tends to ship frontier reasoning models with premium positioning, while Arcee AI often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): MiMo-V2.5-Pro (Non-reasoning) costs $25.95 ($311/year); Trinity Large Thinking costs $20.10 ($241/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): MiMo-V2.5-Pro (Non-reasoning) ≈ $3.89/run, Trinity Large Thinking ≈ $2.91/run. At agent/realtime scale (200M input / 100M output per million requests): MiMo-V2.5-Pro (Non-reasoning) ≈ $173/run, Trinity Large Thinking ≈ $134/run. Trinity Large Thinking becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Head-to-head deltas
Data from Artificial Analysis API — 12 benchmarks
Trinity Large Thinking is cheaper overall. Its blended price (3:1 input/output ratio) is $0.39/M tokens vs $0.54/M for MiMo-V2.5-Pro (Non-reasoning).
It's a tie — both models win 1 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.
Trinity Large Thinking generates tokens faster at 203 tok/s vs 48 tok/s. However, Trinity Large Thinking has lower time-to-first-token (1.23s vs 3.28s).
Choose based on your priorities: Trinity Large Thinking for lower cost, both perform similarly on benchmarks, and Trinity Large Thinking for faster generation. For latency-sensitive apps, check the TTFT comparison above.