Model Comparison
Gemini 2.5 Flash (Reasoning)
vs. MiniCPM-V 4.6 1.3B
Comparing 2 AI models · 12 benchmarks · Google, OpenBMB
Recommended Pick
Go Gemini 2.5 Flash (Reasoning) 10 metric wins Strongest on: Throughput, Reasoning, Intelligence
Lowest Price
MiniCPM-V 4.6 1.3B
$0.00/1M input price
Best Reasoning
Gemini 2.5 Flash (Reasoning)
63.5 reasoning score
Blends available reasoning benchmarks
Best for Coding
Gemini 2.5 Flash (Reasoning)
22.2 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Price gap
MiniCPM-V 4.6 1.3B is ∞x cheaper on input tokens than Gemini 2.5 Flash (Reasoning).
Reasoning gap
Gemini 2.5 Flash (Reasoning) leads MiniCPM-V 4.6 1.3B by 47.4 points on reasoning.
Coding gap
Gemini 2.5 Flash (Reasoning) leads MiniCPM-V 4.6 1.3B by 21.5 points on coding.
Top-pick rationale
Gemini 2.5 Flash (Reasoning) wins 10 measurable categories, including Throughput, Reasoning, Intelligence, Coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Gemini 2.5 Flash (Reasoning)
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
MiniCPM-V 4.6 1.3B
OpenBMB
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Go Gemini 2.5 Flash (Reasoning) | Op MiniCPM-V 4.6 1.3B |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.30/1M | $0.00/1M |
| Output Cost | $2.50/1M | $0.00/1M |
| Blended (3:1) | $0.85/1M | — |
| Specifications | ||
| Organization | OpenBMB | |
| Release Date | May 20, 2025 | May 11, 2026 |
| Performance & Speed | ||
| Throughput | 226.0 tok/s | — |
| TTFT | 14806ms | — |
| Latency | 14806ms | — |
| Composite Indices | ||
| Value Score | 100.0 | — |
| Reasoning Score | 63.5 | 16.0 |
| Intelligence | 27.0 | 12.7 |
| Coding | 22.2 | 0.7 |
| Math | 73.3 | — |
| Standard Benchmarks | ||
| GPQA | 79.0% | 30.5% |
| MMLU Pro | 83.2% | — |
| HLE | 11.1% | 4.9% |
| LiveCodeBench | 69.5% | — |
| MATH 500 | 98.1% | — |
| AIME 2025 | 73.3% | — |
| AIME (Original) | 82.3% | — |
| SciCode | 39.4% | 2.1% |
| LCR | 61.7% | 6.3% |
| IFBench | 50.3% | 26.7% |
| TAU-bench v2 | 31.6% | 87.7% |
| TerminalBench Hard | 13.6% | 0.0% |
Key Takeaways
MiniCPM-V 4.6 1.3B offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Gemini 2.5 Flash (Reasoning) has the strongest reasoning profile with a 63.5 reasoning score, combining the available reasoning-heavy benchmarks.
Gemini 2.5 Flash (Reasoning) reaches a 22.2 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
Gemini 2.5 Flash (Reasoning)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
MiniCPM-V 4.6 1.3B
- Cost-sensitive applications
- High-volume processing
