Sign in

Is EXAONE-4.0-1.2B-JEV v0.3 (unofficial fine-tune of LGAI-EXAONE/EXAONE-4.0-1.2B, native option-label softmax, two reads averaged, self-hosted) SOTA in Decision models?#337 in Decision modelsRanked #337 in Decision models.

How it scores here

EXAONE-4.0-1.2B-JEV v0.3 (unofficial fine-tune of LGAI-EXAONE/EXAONE-4.0-1.2B, native option-label softmax, two reads averaged, self-hosted) in Decision models

Primary benchmarks

  • Decision Index Full: 20.6 (CI 20.1–21.1) on Nov 21, 2026 (#359 of 420).
  • JevBench: 47.7 (CI 47.2–48.2) on Oct 8, 2026 (#90 of 134).

On the category's weighted score it is 75.2 points behind #1 karpo-decision-31B and 0.1 behind the next model up, StartLux-Decision v1.1 0.8B.

Nearby on the board

#ModelCategory score
334Gevva E4B25.2
335Certo v1 (AltSlate Labs)25.0
336StartLux-Decision v1.1 0.8B24.9
337EXAONE-4.0-1.2B-JEV v0.3 (unofficial fine-tune of LGAI-EXAONE/EXAONE-4.0-1.2B, native option-label softmax, two reads averaged, self-hosted)24.8
338openvons24.6
339ClassOne Qwen3.5 4B24.3
340smalljev semantic-v924.2
Standings

Decision models

Category page →