Model Comparison
Solar Pro 2 (Preview) (Non-reasoning)
vs. Tri-21B-think Preview
Comparing 2 AI models · 11 benchmarks · Upstage, Trillion Labs
Recommended Pick
UpSolar Pro 2 (Preview) (Non-reasoning)3 metric winsStrongest on: Reasoning, GPQA, SciCode
Lowest Price
Solar Pro 2 (Preview) (Non-reasoning)
$0.00/1M input price
Best Reasoning
Solar Pro 2 (Preview) (Non-reasoning)
37.0 reasoning score
Blends available reasoning benchmarks
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Reasoning gap
Solar Pro 2 (Preview) (Non-reasoning) leads Tri-21B-think Preview by 12.6 points on reasoning.
Top-pick rationale
Solar Pro 2 (Preview) (Non-reasoning) wins 3 measurable categories, including Reasoning, GPQA, SciCode.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Solar Pro 2 (Preview) (Non-reasoning)
Upstage
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Tri-21B-think Preview
Trillion Labs
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Chat with leading AI models
Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, Qwen & Kimi.
EU-hosted inference
Servers in Germany & Finland. Designed to meet strict GDPR and ISO 27001 compliance requirements.
Full Comparison
| Metric | Top Pick Up Solar Pro 2 (Preview) (Non-reasoning) | Tr Tri-21B-think Preview |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.00/1M |
| Output Cost | $0.00/1M | $0.00/1M |
| Specifications | ||
| Organization | Upstage | Trillion Labs |
| Release Date | May 20, 2025 | Feb 10, 2026 |
| Performance & Speed | ||
| Throughput | — | — |
| TTFT | — | — |
| Latency | — | — |
| Composite Indices | ||
| Reasoning Score | 37.0 | 24.4 |
| Intelligence | 10.0 | 13.6 |
| Standard Benchmarks | ||
| GPQA | 54.4% | 53.8% |
| MMLU Pro | 72.5% | — |
| HLE | 3.8% | 5.7% |
| LiveCodeBench | 38.5% | — |
| MATH 500 | 87.1% | — |
| AIME (Original) | 29.7% | — |
| SciCode | 27.2% | 17.8% |
| LCR | — | 14.7% |
| IFBench | — | 47.1% |
| TAU-bench v2 | — | 93.3% |
| TerminalBench Hard | — | 2.3% |
Key Takeaways
Solar Pro 2 (Preview) (Non-reasoning) offers the best value at $0.00/1M,making it ideal for high-volume applications and cost-conscious projects.
Solar Pro 2 (Preview) (Non-reasoning) has the strongest reasoning profile with a 37.0 reasoning score,combining the available reasoning-heavy benchmarks.
All models support context windows of ∞+ tokens,suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Solar Pro 2 (Preview) (Non-reasoning)
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
Tri-21B-think Preview
- General-purpose AI
- Versatile applications
