Compare/Trinity Large Thinking vs Reka Flash 3

Trinity Large ThinkingvsReka Flash 3

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Arcee AI

Trinity Large Thinking

Input
$0.235/M
Output
$0.875/M
Speed
118 tok/s
TTFT
0.59s
Reka AI

Reka Flash 3

Input
$0.2/M
Output
$0.8/M
Speed
89 tok/s
TTFT
1.22s

Winner by Category

Cheaper
Reka Flash 3
Faster (tok/s)
Trinity Large Thinking
Lower Latency
Trinity Large Thinking
Benchmarks (7-5)
Trinity Large Thinking

Pricing Comparison

MetricTrinity Large ThinkingReka Flash 3
Input ($/M tokens)$0.235$0.2
Output ($/M tokens)$0.875$0.8
Cost for 1M input + 100K output tokens:
Trinity Large Thinking$0.32
Reka Flash 3$0.28

Speed Comparison

Output Speed (tokens/s) — higher is better
Trinity Large Thinking
118 tok/s
Reka Flash 3
89 tok/s
Time to First Token (seconds) — lower is better
Trinity Large Thinking
0.59s
Reka Flash 3
1.22s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
31.99.5
Coding Index
27.28.9
Math Index
33.7
GPQA Diamond
75.2%52.9%
MMLU-Pro
66.9%
LiveCodeBench
43.5%
AIME 2025
33.7%
MATH-500
89.3%
Humanity's Last Exam
14.7%5.1%
SciCode
36.1%26.7%
IFBench
56.3%30.4%
TerminalBench
22.7%0.0%
Trinity Large Thinking7 wins
5 winsReka Flash 3

Frequently Asked Questions

Which is cheaper, Trinity Large Thinking or Reka Flash 3?

Reka Flash 3 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.35/M tokens vs $0.40/M for Trinity Large Thinking.

Which model performs better on benchmarks?

Trinity Large Thinking wins 7 out of 12 benchmarks compared to 5 for Reka Flash 3. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Trinity Large Thinking generates tokens faster at 118 tok/s vs 89 tok/s. Trinity Large Thinking also has lower time-to-first-token (0.59s vs 1.22s).

When should I use Trinity Large Thinking vs Reka Flash 3?

Choose based on your priorities: Reka Flash 3 for lower cost, Trinity Large Thinking for stronger benchmark performance, and Trinity Large Thinking for faster generation. For latency-sensitive apps, check the TTFT comparison above.