Model Comparison
Reka Flash (Sep '24)
vs. Solar Pro 2 (Non-reasoning)
Comparing 2 AI models · 12 benchmarks · Reka AI, Upstage
Recommended Pick
Up Solar Pro 2 (Non-reasoning) 7 metric wins Strongest on: Input price, Output price, TTFT
Lowest Price
Solar Pro 2 (Non-reasoning)
$0.00/1M input price
Best Reasoning
Solar Pro 2 (Non-reasoning)
37.6 reasoning score
Blends available reasoning benchmarks
Best for Coding
Solar Pro 2 (Non-reasoning)
11.3 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
Solar Pro 2 (Non-reasoning) is ∞x cheaper on input tokens than Reka Flash (Sep '24).
Reasoning gap
Solar Pro 2 (Non-reasoning) leads Reka Flash (Sep '24) by 5.1 points on reasoning.
Top-pick rationale
Solar Pro 2 (Non-reasoning) wins 7 measurable categories, including Input price, Output price, TTFT, Latency.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Reka Flash (Sep '24)
Reka AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Solar Pro 2 (Non-reasoning)
Upstage
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Re Reka Flash (Sep '24) | Top Pick Up Solar Pro 2 (Non-reasoning) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.20/1M | $0.00/1M |
| Output Cost | $0.80/1M | $0.00/1M |
| Blended (3:1) | $0.35/1M | — |
| Specifications | ||
| Organization | Reka AI | Upstage |
| Release Date | Oct 4, 2024 | Jul 9, 2025 |
| Performance & Speed | ||
| Throughput | 85.9 tok/s | — |
| TTFT | 1779ms | — |
| Latency | 1779ms | — |
| Composite Indices | ||
| Value Score | 100.0 | — |
| Reasoning Score | 32.4 | 37.6 |
| Intelligence | 12.0 | 13.6 |
| Coding | — | 11.3 |
| Math | — | 30.0 |
| Standard Benchmarks | ||
| GPQA | — | 56.1% |
| MMLU Pro | — | 75.0% |
| HLE | — | 3.8% |
| LiveCodeBench | — | 42.4% |
| MATH 500 | 52.9% | 88.9% |
| AIME 2025 | — | 30.0% |
| AIME (Original) | — | 40.7% |
| SciCode | — | 24.8% |
| LCR | — | 0.0% |
| IFBench | — | 33.7% |
| TAU-bench v2 | — | 31.9% |
| TerminalBench Hard | — | 4.5% |
Key Takeaways
Solar Pro 2 (Non-reasoning) offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Solar Pro 2 (Non-reasoning) has the strongest reasoning profile with a 37.6 reasoning score, combining the available reasoning-heavy benchmarks.
Solar Pro 2 (Non-reasoning) reaches a 11.3 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
Reka Flash (Sep '24)
- General-purpose AI
- Versatile applications
Solar Pro 2 (Non-reasoning)
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
