Model Comparison
R1 Distill Qwen 1.5B
vs. GLM-5.1 (Non-reasoning)
Comparing 2 AI models · 12 benchmarks · DeepSeek, Z AI
Recommended Pick
Z GLM-5.1 (Non-reasoning) 8 metric wins Strongest on: Throughput, Reasoning, Intelligence
Lowest Price
R1 Distill Qwen 1.5B
$0.00/1M input price
Best Reasoning
GLM-5.1 (Non-reasoning)
51.1 reasoning score
Blends available reasoning benchmarks
Best for Coding
GLM-5.1 (Non-reasoning)
35.8 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
R1 Distill Qwen 1.5B is ∞x cheaper on input tokens than GLM-5.1 (Non-reasoning).
Reasoning gap
GLM-5.1 (Non-reasoning) leads R1 Distill Qwen 1.5B by 29.3 points on reasoning.
Top-pick rationale
GLM-5.1 (Non-reasoning) wins 8 measurable categories, including Throughput, Reasoning, Intelligence, GPQA.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
R1 Distill Qwen 1.5B
DeepSeek
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
GLM-5.1 (Non-reasoning)
Z AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | De R1 Distill Qwen 1.5B | Top Pick Z GLM-5.1 (Non-reasoning) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $1.40/1M |
| Output Cost | $0.00/1M | $4.40/1M |
| Blended (3:1) | — | $2.15/1M |
| Specifications | ||
| Organization | DeepSeek | Z AI |
| Release Date | Jan 20, 2025 | Apr 7, 2026 |
| Performance & Speed | ||
| Throughput | — | 59.7 tok/s |
| TTFT | — | 1023ms |
| Latency | — | 1023ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 21.8 | 51.1 |
| Intelligence | 9.1 | 43.8 |
| Coding | — | 35.8 |
| Math | 22.0 | — |
| Standard Benchmarks | ||
| GPQA | 9.8% | 83.9% |
| MMLU Pro | 26.9% | — |
| HLE | 3.3% | 25.6% |
| LiveCodeBench | 7.0% | — |
| MATH 500 | 68.7% | — |
| AIME 2025 | 22.0% | — |
| AIME (Original) | 17.7% | — |
| SciCode | 6.6% | 36.1% |
| LCR | 0.3% | 44.3% |
| IFBench | 13.2% | 52.0% |
| TAU-bench v2 | — | 97.1% |
| TerminalBench Hard | — | 35.6% |
Key Takeaways
R1 Distill Qwen 1.5B offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
GLM-5.1 (Non-reasoning) has the strongest reasoning profile with a 51.1 reasoning score, combining the available reasoning-heavy benchmarks.
GLM-5.1 (Non-reasoning) reaches a 35.8 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
R1 Distill Qwen 1.5B
- Cost-sensitive applications
- High-volume processing
GLM-5.1 (Non-reasoning)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
