Model Comparison
Devstral Small (May '25)
vs. GLM-4.7-Flash (Reasoning)
Comparing 2 AI models · 11 benchmarks · Mistral, Z AI
Recommended Pick
Z GLM-4.7-Flash (Reasoning) 11 metric wins Strongest on: Throughput, Reasoning, Intelligence
Lowest Price
Devstral Small (May '25)
$0.00/1M input price
Best Reasoning
GLM-4.7-Flash (Reasoning)
31.8 reasoning score
Blends available reasoning benchmarks
Best for Coding
GLM-4.7-Flash (Reasoning)
25.9 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
Devstral Small (May '25) is ∞x cheaper on input tokens than GLM-4.7-Flash (Reasoning).
Reasoning gap
GLM-4.7-Flash (Reasoning) leads Devstral Small (May '25) by 3.7 points on reasoning.
Coding gap
GLM-4.7-Flash (Reasoning) leads Devstral Small (May '25) by 13.7 points on coding.
Top-pick rationale
GLM-4.7-Flash (Reasoning) wins 11 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.
Devstral Small (May '25)
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
GLM-4.7-Flash (Reasoning)
Z AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Mi Devstral Small (May '25) | Top Pick Z GLM-4.7-Flash (Reasoning) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.07/1M |
| Output Cost | $0.00/1M | $0.40/1M |
| Blended (3:1) | — | $0.15/1M |
| Specifications | ||
| Organization | Mistral | Z AI |
| Release Date | May 21, 2025 | Jan 19, 2026 |
| Performance & Speed | ||
| Throughput | — | 87.1 tok/s |
| TTFT | — | 906ms |
| Latency | — | 23872ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 28.1 | 31.8 |
| Intelligence | 18.0 | 30.1 |
| Coding | 12.2 | 25.9 |
| Standard Benchmarks | ||
| GPQA | 43.4% | 58.1% |
| MMLU Pro | 63.2% | — |
| HLE | 4.0% | 7.1% |
| LiveCodeBench | 25.8% | — |
| MATH 500 | 68.4% | — |
| AIME (Original) | 6.7% | — |
| SciCode | 24.5% | 33.7% |
| LCR | 26.7% | 35.0% |
| IFBench | 31.6% | 60.8% |
| TAU-bench v2 | 38.0% | 98.8% |
| TerminalBench Hard | 6.1% | 22.0% |
Key Takeaways
Devstral Small (May '25) offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
GLM-4.7-Flash (Reasoning) has the strongest reasoning profile with a 31.8 reasoning score, combining the available reasoning-heavy benchmarks.
GLM-4.7-Flash (Reasoning) reaches a 25.9 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
Devstral Small (May '25)
- Cost-sensitive applications
- High-volume processing
GLM-4.7-Flash (Reasoning)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Recommended Comparisons
Popular alternatives
