Model Comparison
Gemini 1.5 Flash (Sep '24)
vs. MiniCPM-V 4.6 1.3B
Comparing 2 AI models · 11 benchmarks · Google, OpenBMB
Recommended Pick
Go Gemini 1.5 Flash (Sep '24) 4 metric wins Strongest on: Reasoning, Intelligence, GPQA
Lowest Price
Gemini 1.5 Flash (Sep '24)
$0.00/1M input price
Best Reasoning
Gemini 1.5 Flash (Sep '24)
32.9 reasoning score
Blends available reasoning benchmarks
Best for Coding
MiniCPM-V 4.6 1.3B
0.7 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Reasoning gap
Gemini 1.5 Flash (Sep '24) leads MiniCPM-V 4.6 1.3B by 16.8 points on reasoning.
Top-pick rationale
Gemini 1.5 Flash (Sep '24) wins 4 measurable categories, including Reasoning, Intelligence, GPQA, SciCode.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Gemini 1.5 Flash (Sep '24)
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 1.5 Flash (Sep '24) | Op MiniCPM-V 4.6 1.3B |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.00/1M |
| Output Cost | $0.00/1M | $0.00/1M |
| Specifications | ||
| Organization | OpenBMB | |
| Release Date | Sep 24, 2024 | May 11, 2026 |
| Performance & Speed | ||
| Throughput | — | — |
| TTFT | — | — |
| Latency | — | — |
| Composite Indices | ||
| Reasoning Score | 32.9 | 16.0 |
| Intelligence | 13.8 | 12.7 |
| Coding | — | 0.7 |
| Standard Benchmarks | ||
| GPQA | 46.3% | 30.5% |
| MMLU Pro | 68.0% | — |
| HLE | 3.5% | 4.9% |
| LiveCodeBench | 27.3% | — |
| MATH 500 | 82.7% | — |
| AIME (Original) | 18.0% | — |
| SciCode | 26.7% | 2.1% |
| LCR | — | 6.3% |
| IFBench | — | 26.7% |
| TAU-bench v2 | — | 87.7% |
| TerminalBench Hard | — | 0.0% |
Key Takeaways
Gemini 1.5 Flash (Sep '24) offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Gemini 1.5 Flash (Sep '24) has the strongest reasoning profile with a 32.9 reasoning score, combining the available reasoning-heavy benchmarks.
MiniCPM-V 4.6 1.3B reaches a 0.7 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 1.5 Flash (Sep '24)
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
MiniCPM-V 4.6 1.3B
- Code generation
- Software development
