whatmodel.sh / Reka Flash (2024-09-04)
Reka Flash (2024-09-04)
↗ share
+ contribute
Reka Flash (2024-09-04) is a closed-weights language model from Reka AI, released September 2024.
Catalogue identity notes
Comparison-only. Arena entry 'reka-flash-20240904' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'reka-flash-20240904' as 'Reka-Flash-20240904' (Reka AI, Proprietary), linking https://docs.reka.ai/available-models. Released 2024-09: date in Reka's API snapshot id. Dated Reka API snapshot. Reka's current docs list only reka-flash (a newer model) and reka-edge as public models.
$ how it compares
The LLMs ranked either side of Reka Flash (2024-09-04), out of 1132 with a score, then more from Reka AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 552 |  Athene-70B | 51±1 | local | ||
| 553 |  Qwen2 72B Instruct | 51±1 | local | ||
| 554 | Reka Flash (2024-09-04) | 51±3 | comparison only | ||
| 555 |  Bielik 11B v2.0 Instruct | 51±3 | local | ||
| 556 |  Solar Pro Preview (22B) | 51±7 | local | ||
| more from Reka AI | |||||
| 505 | Reka Flash 3 (21B) | 52±6 | local | ||
| 507 | Reka Core (2024-09-04) | 52±3 | comparison only | ||
| 523 | Reka Flash 3.1 (21B) | 52±6 | local | ||
$ what it's good at
chat & writing▁▁▁▃▅▅▆█▆▆▆▂ #358 of 579 * · 95% of its score · 1 test
Beats Mistral Small 4 (119B-A6.5B), Ministral 3 14B Reasoning 2512, Qwen2.5 Coder 32B Instruct here, though they rank higher overall. Trails Flan-T5 XXL, Granite 4.0 H 1B, Granite 4.0 1B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1272.4 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 104/379 | 95% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 95%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 1 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 50.5 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json