whatmodel.sh / decision / decider-4b v2.1 (JevBench mini)
decider-4b v2.1 (JevBench mini)
↗ share
+ contribute
decider-4b v2.1 (JevBench mini) is a source-available decision implementation from Mapika.
Catalogue identity notes
JevBench 0.1.0 mini tested configuration decider-4b: Decoder, answer-letter logits; base Qwen3.5-4B-Base; readout full fine-tune + LoRA stage; option-letter logits, per-type temperatures. Separate identity because the report does not establish equivalence to the newer Decision Index checkpoint or serving recipe. No latency imported.
$ how it compares
The decision models ranked either side of decider-4b v2.1 (JevBench mini), out of 357 with a score, then more from Mapika.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 173 |  JevAny-Qwen-4B (pointer) (JevBench mini) | 54±2 | source code | ||
| 174 |  Standard One 3B SH (v4) | 54±1 | model files | ||
| 175 | decider-4b v2.1 (JevBench mini) | 54±2 | source code | ||
| 176 |  vLLM-SR Decision 2.0 Lux 9B | 54±1 | local | ||
| 177 | JevAny-Gemma-4B (pointer) (JevBench mini) | 54±2 | source code | ||
| more from Mapika | |||||
| 43 | Decider 31B (NVFP4) | 66±1 | model files | ||
| 85 | Decider chat · Gemma-4-31B (decision readout) | 62±1 | source code | ||
| 110 | decider-35b-a3b (DecisionBench d9783c58) | 60±2 | model files | ||
see all decision models · find the ones that fit your machine
$ what it's good at
tools & automation▁▃▁▁▁▂▃▄▆██▆ #124 of 250 * · 16% of its score · 2 tests
Beats Tern-35B-A3B, GEV-26B-Decide, Cerno 4B v1.1 here, though they rank higher overall. Trails OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B, razorback16 diffgemma (decision readout) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AgentDecisionBench: L1 BFCL v4 + When2Call (3,991 items) | 79.3% ✎ | █·····▄·▄▄·▄ beats 3/5 | 9.0% |
| AgentDecisionBench: L2 DecisionGym common states (200 tasks) | 63.2% ✎ | ██···█·██··█ beats 3/5 | 7.3% |
consistency▃·▂▂·▅▃·▃▅▃█ #4 of 21 · 58% of its score · 5 tests
Trails JevAny-Gemma-4B (pointer) (JevBench mini) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| JevBench mini 0.1.0 · Probability measure coherence (pass rate) | 52.5% ✎ | ▄·▁·▃▃▁·▃▄▁█ beats 20/20 | 44% |
| JevBench mini 0.1.0 · Representation consistency (pass rate) | 80.3% ✎ | ▃·▂·▂▂▂▃▅▅▃█ beats 15/20 | 11% |
| JevBench mini 0.1.0 · Logical coherence (pass rate) | 78.8% ✎ | ▃·▃·█▅▅██▃█▅ beats 13/20 | 1.9% |
| JevBench mini 0.1.0 · Choice-set coherence (pass rate) | 80.6% ✎ | ▁▃▄█▄▄·····▄ beats 12/20 | 1.0% |
| JevBench mini 0.1.0 · Batch independence (pass rate) | 100.0% ✎ | ▁··········█ beats 17/20 | 0.0% |
other tests1 not in a task · 24% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| JevBench mini 0.1.0 · unchanged-answer accuracy | 88.6% ✎ | ▁·▂·▂···▂▂▁█ beats 16/20 | 24% |
$ where to run it
Implementation and setup instructions ↗
Published implementation and setup documentation verified. This entry describes a decision readout or evaluated configuration, not necessarily separate trained weights. Follow the referenced version and model settings; hardware compatibility has not been verified. Source · checked 2026-10-31.
Model repository and documentation: github.com/Mapika ↗
$ how the score was worked out · JevBench 0.1.0 mini evaluatio… 82%, AgentDecisionBench 16%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 JevBench 0.1.0 mini evaluation reports | 6 | 82% |
| AgentDecisionBench | 2 | 16% |
| prior · pull toward the middle | 2% | |
| weighted average | = 53.8 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json