Strands Decider Release - JevBench Brier: leaderboard

Strands Decider Release - JevBench Brier: Native task score. Official Strands decider release table: four explicitly linked gemma4-v1-2610 trained decision checkpoints, bf16 weights. JevBench correct counts out of 231, Brier error 0-2, held-out short/code accuracy fractions and native Decision Index 0-100. Latency and memory omitted. The separate Qwen3.5-2B checkpoint is not the Gemma E2B model.

Metric: Native task score. Source: raw.githubusercontent.com. Saturation forecast: Rough model projection: around 2026. 4 models tracked.

Top models

#ModelScoreOverall rank
1strands-decider-26B-A4B-gemma4-v1-26100.16
2strands-decider-12B-gemma4-v1-26100.17
3strands-decider-E4B-gemma4-v1-26100.24
4strands-decider-E2B-gemma4-v1-26100.31

Interactive version: theaggregate.ai/benchmark?slug=strands-decider-release-jevbench-brier · How It Works · Data refreshed daily, snapshot 2026-11-12.