Quality
Highest overall scores
- 1
Reka Edge0 - 2Reka Flash 30
Reka AI model benchmarks.
Compare Reka AI models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1Reka Flash 347 t/s
- 2Reka Edge7 t/s
Input price
Lowest price per 1M tokens
- 1Reka Edge$0.10/1M
- 2Reka Flash 3$0.10/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare Reka AI model capability.
Performance and price
Compare practical tradeoffs.
All Reka AI models.
2 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| Reka Edge | 0 | 7 t/s | 16.4K | $0.10 | $0.10 | |
| Reka Flash 3 | 0 | 47 t/s | 65.5K | $0.10 | $0.20 |
Reka AI technical benchmarks.
Compare named evaluation records available for Reka AI models. Missing results remain blank rather than being estimated.
| Benchmark | Area | Reka Edge | Reka Flash 3 | Source |
|---|---|---|---|---|
| GPQA | GPQA Diamond | — | 52.9 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | — | 4.4 | OpenRouter model benchmarks |
| IFBench | IFBench | — | 30.4 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | — | 0 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | — | 0 | OpenRouter model benchmarks |
| CritPt | CritPt | — | 0 | OpenRouter model benchmarks |
| SciCode | SciCode | — | 26.7 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | — | 0 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | — | 13.7 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | — | 8.7 | OpenRouter model benchmarks |