Reka Flash 3: benchmark scores, price and ranking
Reka Flash 3 from rekaai ranks #260 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.5), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- rekaai
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-03-10 (source: epoch)
- Context window
- 65,536 tokens
- Cheapest API price
- $0.100 in / $0.200 out per million tokens (via openrouter, observed 2026-10-13T20:47Z)
- Aggregate rank
- #260 of 743 (score 49.5)
Across the 1 benchmark where at least ten models are scored, Reka Flash 3 is in the top 10% on 0 and in the top half on 1.
Its cheapest listed input price, $0.100 per million tokens, is lower than that of 79% of the 427 models with a listed price.
Reka Flash 3 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| BALROG | 29.2% | #16 of 34 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Reka Flash 3
Reka Flash 3 is an open-weight model that can run on your own hardware from rekaai. It was released on 2025-03-10, according to Epoch AI. It accepts up to 65,536 tokens of input at once. The cheapest API listing we track charges $0.100 per million input tokens and $0.200 per million output tokens, through openrouter. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Reka Flash 3 stands
On our aggregate score, Reka Flash 3 is #260 of 743 ranked models, around the middle of the table. Its score is 49.5; the scale is centred on 50, so it sits 0.5 points below the typical model. That beats 65% of the ranked field.
Reka Flash 3, benchmark by benchmark
BALROG puts Reka Flash 3 at 29.2%, #16 of 34. That beats 53% of the models tested, but 39.1 points short of GPT-6 Astra (max) (68.3%). The results either side are grok-3-beta (29.5%) and Llama-3.1-70B-Instruct (27.9%). It covers long-horizon game-playing agents. The board median is 27.6%, so Reka Flash 3 is 1.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Reka Flash 3 costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on Qwen3.8 Flash (xhigh) ($0.113) and GLM-4.5-Air ($0.125).
Reading these numbers
The 1 score on this page comes from 1 source: Epoch AI Benchmarking Hub (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #257 claude-haiku-4-5-20251001_16K (49.5)
- #258 Kimi-K2-Instruct-0905 (49.5)
- #259 mimo-v2.5-pro (49.5)
- #261 gemini-exp-1121 (49.5)
- #262 gpt-3.5-turbo-0301 (49.5)
- #263 Qwen2.5-Coder-7B-Instruct (49.5)
Compare it on the live leaderboard → · How the aggregate score works