Model Comparison
MiMo-V2.5
vs. Small 3.1
Comparing 2 AI models · 12 benchmarks · Xiaomi, Mistral
Recommended Pick
Xi MiMo-V2.5 11 metric wins Strongest on: Value, Reasoning, Intelligence
Best Value
MiMo-V2.5
100.0 value score
50.1 reasoning / $0.18/1M
Lowest Price
Small 3.1
$0.10/1M input price
Best Reasoning
MiMo-V2.5
50.1 reasoning score
Blends available reasoning benchmarks
Best for Coding
MiMo-V2.5
42.1 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
MiMo-V2.5 has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Small 3.1 is 1.3x cheaper on input tokens than MiMo-V2.5.
Speed gap
Small 3.1 generates about 2.1x as many tokens per second as MiMo-V2.5.
Reasoning gap
MiMo-V2.5 leads Small 3.1 by 29.2 points on reasoning.
Coding gap
MiMo-V2.5 leads Small 3.1 by 28.2 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
MiMo-V2.5
Xiaomi
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Small 3.1
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Xi MiMo-V2.5 | Mi Small 3.1 |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.14/1M | $0.10/1M |
| Output Cost | $0.28/1M | $0.23/1M |
| Blended (3:1) | $0.18/1M | $0.14/1M |
| Specifications | ||
| Organization | Xiaomi | Mistral |
| Release Date | Apr 22, 2026 | Mar 17, 2025 |
| Performance & Speed | ||
| Throughput | 72.4 tok/s | 152.4 tok/s |
| TTFT | 1931ms | 532ms |
| Latency | 29541ms | 532ms |
| Composite Indices | ||
| Value Score | 100.0 | 53.1 |
| Reasoning Score | 50.1 | 20.9 |
| Intelligence | 40.1 | 8.6 |
| Coding | 42.1 | 13.9 |
| Math | — | 3.7 |
| Standard Benchmarks | ||
| GPQA | 84.9% | 45.4% |
| MMLU Pro | — | 65.9% |
| HLE | 25.2% | 4.8% |
| LiveCodeBench | — | 21.2% |
| MATH 500 | — | 70.7% |
| AIME 2025 | — | 3.7% |
| AIME (Original) | — | 9.3% |
| SciCode | 43.1% | 26.5% |
| LCR | 62.7% | 19.7% |
| IFBench | 67.1% | 29.9% |
| TAU-bench v2 | 90.6% | 25.1% |
| TerminalBench Hard | 41.7% | 7.6% |
Key Takeaways
Small 3.1 offers the best value at $0.10/1M, making it ideal for high-volume applications and cost-conscious projects.
MiMo-V2.5 has the strongest reasoning profile with a 50.1 reasoning score, combining the available reasoning-heavy benchmarks.
MiMo-V2.5 reaches a 42.1 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
MiMo-V2.5
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Small 3.1
- Cost-sensitive applications
- High-volume processing
