Model Comparison
GLM-4.7-Flash (Non-reasoning)
vs. Small 3
Comparing 2 AI models · 12 benchmarks · Z AI, Mistral
Recommended Pick
Z GLM-4.7-Flash (Non-reasoning) 8 metric wins Strongest on: Input price, Reasoning, Intelligence
Best Value
Small 3
100.0 value score
20.8 reasoning / $0.10/1M
Lowest Price
GLM-4.7-Flash (Non-reasoning)
$0.07/1M input price
Best Reasoning
GLM-4.7-Flash (Non-reasoning)
21.9 reasoning score
Blends available reasoning benchmarks
Best for Coding
GLM-4.7-Flash (Non-reasoning)
11.0 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
Small 3 has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
GLM-4.7-Flash (Non-reasoning) is 1.1x cheaper on input tokens than Small 3.
Speed gap
Small 3 generates about 1.6x as many tokens per second as GLM-4.7-Flash (Non-reasoning).
Reasoning gap
GLM-4.7-Flash (Non-reasoning) leads Small 3 by 1.1 points on reasoning.
Top-pick rationale
GLM-4.7-Flash (Non-reasoning) wins 8 measurable categories, including Input price, Reasoning, Intelligence, HLE.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
GLM-4.7-Flash (Non-reasoning)
Z AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Small 3
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Z GLM-4.7-Flash (Non-reasoning) | Mi Small 3 |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.07/1M | $0.07/1M |
| Output Cost | $0.40/1M | $0.19/1M |
| Blended (3:1) | $0.15/1M | $0.10/1M |
| Specifications | ||
| Organization | Z AI | Mistral |
| Release Date | Jan 19, 2026 | Jan 30, 2025 |
| Performance & Speed | ||
| Throughput | 114.3 tok/s | 182.7 tok/s |
| TTFT | 1247ms | 543ms |
| Latency | 1247ms | 543ms |
| Composite Indices | ||
| Value Score | 71.6 | 100.0 |
| Reasoning Score | 21.9 | 20.8 |
| Intelligence | 15.5 | 6.9 |
| Coding | 11.0 | — |
| Math | — | 4.3 |
| Standard Benchmarks | ||
| GPQA | 45.2% | 46.2% |
| MMLU Pro | — | 65.2% |
| HLE | 4.9% | 4.1% |
| LiveCodeBench | — | 25.2% |
| MATH 500 | — | 71.5% |
| AIME 2025 | — | 4.3% |
| AIME (Original) | — | 8.0% |
| SciCode | 25.5% | 23.6% |
| LCR | 14.7% | 0.0% |
| IFBench | 46.3% | 26.4% |
| TAU-bench v2 | 91.8% | 19.6% |
| TerminalBench Hard | 3.8% | — |
Key Takeaways
GLM-4.7-Flash (Non-reasoning) offers the best value at $0.07/1M, making it ideal for high-volume applications and cost-conscious projects.
GLM-4.7-Flash (Non-reasoning) has the strongest reasoning profile with a 21.9 reasoning score, combining the available reasoning-heavy benchmarks.
GLM-4.7-Flash (Non-reasoning) reaches a 11.0 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
GLM-4.7-Flash (Non-reasoning)
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Small 3
- General-purpose AI
- Versatile applications
