| { |
| "left": { |
| "big": "73.6% on JevBench", |
| "sub": "+9.5 points over our 0.8B v3; Jev 86.6%", |
| "tokens": "25,600 tokens per call, no option cap" |
| }, |
| "rows": [ |
| { |
| "label": "Jev 1.13 (API)", |
| "accuracy": 0.8658008658008658, |
| "pct_1dp": 86.6 |
| }, |
| { |
| "label": "2B v3 \u00b7 this model", |
| "accuracy": 0.7359307359307359, |
| "pct_1dp": 73.6 |
| }, |
| { |
| "label": "decider-2b", |
| "accuracy": 0.70995670995671, |
| "pct_1dp": 71.0 |
| }, |
| { |
| "label": "Open-Jev 2B", |
| "accuracy": 0.645021645021645, |
| "pct_1dp": 64.5 |
| }, |
| { |
| "label": "0.8B v3", |
| "accuracy": 0.6406926406926406, |
| "pct_1dp": 64.1 |
| }, |
| { |
| "label": "Laya", |
| "accuracy": 0.5844155844155844, |
| "pct_1dp": 58.4 |
| } |
| ], |
| "shown": "Shown: Qwen3.5-2B-family systems, our 0.8B v3, Laya and Jev \u00b7 42 of 82 board systems score higher than 73.6%", |
| "note": "231 public items. 2B v3: self-run with the official harness (GGUF F16), not an official board entry; 95% CI 67.6\u201378.9%, so the lead over decider-2b is inside the CI. Other rows as published on the v1.4.1 board.", |
| "sources": [ |
| "figures/jevbench.data.json" |
| ] |
| } |
