- VQA-V2 88.4
- MLVU 74.3
- MMVU 71.7
- Mean of RefCOCO-A 93.13 / RefCOCO-B 86.70 89.9
- VideoHallucer 59.6
- Mobile Actions 88.4
Reka Edge
Reka Edge ranks first on VQAv2.
18
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Reka Mar 2026
Reka Edge
Open weights Small
No Epoch Capabilities Index score yet
- ZeroBench 0% #76 /76
- MMVU 71.7% #13 /26
- MM-Vet 40.5% #122 /164
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-CN v1.1 | 56.6% | #154 of 178 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 4 | #187 of 188 | Official leaderboard | |
| Mobile Actions | 88.4% | #1 of 1 | Lab model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| VQAv2 | 88.4% | #1 of 8 | Lab model card | |
| RefCOCO / RefCOCO+ / RefCOCOg | 89.9% | #14 of 29 | Lab model card | |
| MMVU | 71.7% | #13 of 26 | Lab model card | |
| CoreCognition | 53.5% | #76 of 119 | Official leaderboard | |
| MM-Vet | 40.5% | #122 of 164 | Official leaderboard | |
| MMMU | 42.8% | #109 of 136 | Official leaderboard | |
| CharXiv | 23.5% | #62 of 77 | Official leaderboard | |
| MMBench | 66.4% | #128 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 63.6% | #151 of 178 | Official leaderboard | |
| MLVU | 74.3% | #20 of 22 | Lab model card | |
| CharXiv (DQ) | 33.6% | #63 of 67 | Official leaderboard | |
| ZeroBench | 0% | #76 of 76 | Official leaderboard | |
| VideoHallucer | 59.6% | #1 of 1 | Lab model card |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AILuminate Safety 1.2 | 11.0 | #5 of 5 | Official leaderboard | |
| MLCommons AILuminate | 11% | #5 of 5 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.