GLiDE vs Jev 1.13
| Benchmark | GLiDE | Jev 1.13 |
|---|---|---|
| AA Decision Index v1.0 | 53.9 | 57.5 |
| AA Decision · Humanity's Last Exam text multiple-choice accuracy | 10.5 | 20.9 |
| AA Decision · Omniscience accuracy | 36.4 | 34.6 |
| AA Decision · Omniscience non-hallucination rate | 16.4 | 35.2 |
| AA Decision · When2Call accuracy | 83.7 | 80.7 |
| AA Decision · WildGuardTest average F1 | 95.1 | 93.6 |
| AA Decision cost per task v1.0 | 0 | 0 |
| AA Decision time per task v1.0 | 217 | 127 |
| Community Decision Index 0.4.1 | 62.4 | 59.2 |
Specs
| Spec | GLiDE | Jev 1.13 |
|---|---|---|
| Input, per 1M | !$0.15 | !$0.042 |
| Context | 40K | 64K |
| Weights | Closed | Closed |
| Released | Sep 2026 | Sep 2026 |
| See images | ✓ | ✓ |
| Read PDFs | — | — |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | — | — |
| Force a tool call | ? | ? |
| Return strict JSON | Partial | Partial |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
GLiDE → Jev 1.13
Nothing known.
Jev 1.13 → GLiDE