Model Comparison
Reka Flash (Sep '24)
vs. Trinity Large Thinking
Comparing 2 AI models · 8 benchmarks · Reka AI, Arcee AI
Recommended Pick
Ar Trinity Large Thinking 5 metric wins Strongest on: Value, Throughput, TTFT
Best Value
Trinity Large Thinking
100.0 value score
40.6 reasoning / $0.40/1M
Lowest Price
Reka Flash (Sep '24)
$0.20/1M input price
Best Reasoning
Trinity Large Thinking
40.6 reasoning score
Blends available reasoning benchmarks
Best for Coding
Trinity Large Thinking
27.2 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
Trinity Large Thinking has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Reka Flash (Sep '24) is 1.2x cheaper on input tokens than Trinity Large Thinking.
Speed gap
Trinity Large Thinking generates about 2.1x as many tokens per second as Reka Flash (Sep '24).
Reasoning gap
Trinity Large Thinking leads Reka Flash (Sep '24) by 8.2 points on reasoning.
Top-pick rationale
Trinity Large Thinking wins 5 measurable categories, including Value, Throughput, TTFT, Reasoning.
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
—
Trinity Large Thinking
Arcee AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Re Reka Flash (Sep '24) | Top Pick Ar Trinity Large Thinking |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.20/1M | $0.23/1M |
| Output Cost | $0.80/1M | $0.88/1M |
| Blended (3:1) | $0.35/1M | $0.40/1M |
| Specifications | ||
| Organization | Reka AI | Arcee AI |
| Release Date | Oct 4, 2024 | Apr 1, 2026 |
| Performance & Speed | ||
| Throughput | 85.8 tok/s | 183.4 tok/s |
| TTFT | 1779ms | 818ms |
| Latency | 1779ms | 11720ms |
| Composite Indices | ||
| Value Score | 90.2 | 100.0 |
| Reasoning Score | 32.4 | 40.6 |
| Intelligence | 12.0 | 31.9 |
| Coding | — | 27.2 |
| Standard Benchmarks | ||
| GPQA | — | 75.2% |
| HLE | — | 14.7% |
| MATH 500 | 52.9% | — |
| SciCode | — | 36.1% |
| LCR | — | 33.0% |
| IFBench | — | 56.3% |
| TAU-bench v2 | — | 90.1% |
| TerminalBench Hard | — | 22.7% |
Key Takeaways
Reka Flash (Sep '24) offers the best value at $0.20/1M, making it ideal for high-volume applications and cost-conscious projects.
Trinity Large Thinking has the strongest reasoning profile with a 40.6 reasoning score, combining the available reasoning-heavy benchmarks.
Trinity Large Thinking reaches a 27.2 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)
- Cost-sensitive applications
- High-volume processing
Trinity Large Thinking
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
