Decider v1.2 vs Jev 1.14
AA Decision Index v1.0 AA Decision Index v1.0: Decision models answer factual and multiple-choice questions and classify tool-use and safety cases in the AA composite
Decider v1.256.2
Jev 1.1457.1
AA Decision · Humanity's Last Exam text multiple-choice accuracy AA Decision · HLE text MCQ accuracy: Decision models select answers to text-only Humanity’s Last Exam multiple-choice questions
Decider v1.214.6
Jev 1.1418.9
AA Decision · Omniscience accuracy AA Decision · Omniscience accuracy: Decision models select correct answers to factual knowledge questions
Decider v1.239.4
Jev 1.1433.8
AA Decision · Omniscience non-hallucination rate AA Decision · Omniscience non-hallucination rate: Decision models answer factual questions, scored on avoiding incorrect assertions
Decider v1.216.5
Jev 1.1437.2
AA Decision · When2Call accuracy AA Decision · When2Call accuracy: Decision models decide when a request requires a tool call
Decider v1.287.7
Jev 1.1480.8
AA Decision · WildGuardTest average F1 AA Decision · WildGuardTest average F1: Decision models classify safety-related inputs, scored by average F1
Decider v1.294.4
Jev 1.1493.1
AA Decision cost per task v1.0 AA Decision cost per task v1.0: Decision models run the AA decision workload, measured by cost per task · lower is better
Decider v1.20
Jev 1.140
AA Decision time per task v1.0 AA Decision time per task v1.0: Decision models run the AA decision workload, measured by elapsed time per task · lower is better
Decider v1.2206
Jev 1.1478
Community Decision Index 0.4.1 Community Decision Index 0.4.1: Decision models answer typed questions across knowledge, language, retrieval, tools and arts tasks
Decider v1.268
Jev 1.14—
| Benchmark | Decider v1.2 | Jev 1.14 |
|---|---|---|
| AA Decision Index v1.0 | 56.2 | 57.1 |
| AA Decision · Humanity's Last Exam text multiple-choice accuracy | 14.6 | 18.9 |
| AA Decision · Omniscience accuracy | 39.4 | 33.8 |
| AA Decision · Omniscience non-hallucination rate | 16.5 | 37.2 |
| AA Decision · When2Call accuracy | 87.7 | 80.8 |
| AA Decision · WildGuardTest average F1 | 94.4 | 93.1 |
| AA Decision cost per task v1.0 | 0 | 0 |
| AA Decision time per task v1.0 | 206 | 78 |
| Community Decision Index 0.4.1 | 68 | — |
Specs
| Spec | Decider v1.2 | Jev 1.14 |
|---|---|---|
| Input, per 1M | !$0.02 | !$0.042 |
| Context | 262K | 64K |
| Weights | Open | Closed |
| Released | Oct 2026 | Oct 2026 |
| Memory (4-bit) | 15 GB | — |
| Licence | Apache-2.0 | — |
| Commercial use | Allowed | — |
| 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
Decider v1.2 → Jev 1.14
Context: 262K → 64K
Jev 1.14 → Decider v1.2
Nothing known.