Issues

• Request: item files for the newer published open-set items (beyond the 231 in datasets/public)

  fstandhartinger/jevbench#240 · Filter by author mengjun-blackboxai opened on Nov 7, 2026
  2

• EvalScope evaluation for the pinned JevBench public subset

  fstandhartinger/jevbench#239 · Filter by author Yunnglin opened on Nov 4, 2026
  2

• [bench request]: nullspan v1.2.1 (open weights, 435M DeBERTa-v3 System One cross-encoder, /v1/systemone server)

  fstandhartinger/jevbench#238 · Filter by author hemanth opened on Oct 30, 2026
  3

• Request to benchmark: Xing4.0-29B-Intent (open weights)

  fstandhartinger/jevbench#236 · Filter by author vivi7d opened on Oct 27, 2026
  2

• [bench request]: Synaps-Decision-1.0-27B-Preview (open weights, LoRA on Qwen3.8-27B)

  fstandhartinger/jevbench#235 · Filter by author PapeMati98 opened on Oct 26, 2026
  4

• Base-model reference price on the vLLM-SR d3 and d3-turbo rows: refresh at the next price cut-off?

  fstandhartinger/jevbench#234 · Filter by author Xunzhuo opened on Oct 26, 2026
  3

• [bench request]: DecisionNode and DecisionNode Flash (hosted API, /v1/systemone)

  fstandhartinger/jevbench#232 · Filter by author bynnit opened on Oct 25, 2026
  6

• Benchmark proposal: DataJevBench — a data-processing decision evaluation for JevBench

  fstandhartinger/jevbench#230 · Filter by author helloml0326 opened on Oct 22, 2026
  3

• Benchmark proposal: HarnessJevBench — a harness runtime control evaluation for JevBench

  fstandhartinger/jevbench#229 · Filter by author helloml0326 opened on Oct 22, 2026
  3

• [bench request]: Mica v0.5 4B (open weights, LoRA fine-tune of Qwen3.5-4B, /v1/systemone server)

  fstandhartinger/jevbench#228 · Filter by author akivet opened on Oct 22, 2026
  4

• [bench request]: Yev-Decision-1 (open weights, 4B, runs locally)

  fstandhartinger/jevbench#225 · Filter by author CodeHalwell opened on Oct 21, 2026
  5

• System submission: Selena OS System One Decision Core (selena-v1-system-one)

  fstandhartinger/jevbench#224 · Filter by author JanuszSikora-Selena-OS opened on Oct 20, 2026
  7

• Dataset proposal: financial market event prediction

  fstandhartinger/jevbench#221 · Filter by author xiangchen-Z opened on Oct 19, 2026
  3

• Jebadiah 9B v2.1 and 27B v2.1 for JevBench

  fstandhartinger/jevbench#220 · Filter by author webdevtodayjason opened on Oct 16, 2026
  2

• [bench request]: Chon-1.0-12B (open weights, self-hosted)

  fstandhartinger/jevbench#219 · Filter by author xoai opened on Oct 15, 2026
  3

• Evaluation request: Respan Span-02 - Open Weights, Self-hosted

  fstandhartinger/jevbench#215 · Filter by author lihe07 opened on Oct 13, 2026
  6

• Brazilian Portuguese typed-decision track

  fstandhartinger/jevbench#202 · Filter by author antonio-mello-ai opened on Oct 10, 2026
  3

• [bench request]: Strands Decider v21 pruned 1.4B (unofficial; Qwen3.5-2B-Base, 15 of 24 layers, native typed probabilities, Apache-2.0)

  fstandhartinger/jevbench#201 · Filter by author alxnahas opened on Oct 9, 2026
  2

• [bench request]: mc-one-draft 12b (frozen google/gemma-4-12B-it, one-token letter readout, TypeSafe wire format)

  fstandhartinger/jevbench#196 · Filter by author kienbui1995 opened on Oct 7, 2026
  4

• Model evaluation request: decision-stack-0.8b-v0.1 (runnable offline bundle)

  fstandhartinger/jevbench#190 · Filter by author mrmps opened on Oct 4, 2026
  3

• Proposal: Traditional Chinese (zh-TW) evaluation slice, with Plumb-4B results on Ollama

  fstandhartinger/jevbench#187 · Filter by author wuchengwei1996 opened on Oct 4, 2026
  3

• [bench request]: Add mentat-sys1-v0.1 (Qwen3.5-4B + LoRA/readout, TypeSafe wire format, self-hosted)

  fstandhartinger/jevbench#186 · Filter by author cloud-qu opened on Oct 4, 2026
  4

• [bench request]: Reflex Reason 2B and Reflex Instinct 0.6B (Atlas AI; open weights, /v1/systemone, self-hosted)

  fstandhartinger/jevbench#184 · Filter by author leemadov opened on Oct 3, 2026
  3

• [bench request]: Add a general-purpose local LLM as-is — Qwen3.8-Flash-Next NVFP4 (vLLM), one-token logprobs readout

  fstandhartinger/jevbench#180 · Filter by author DakotaTexas opened on Oct 2, 2026
  3

• [bench request]: Nadir Scout 12B — frozen Gemma, Cygnet recipe, independent GCP reproduction

  fstandhartinger/jevbench#177 · Filter by author doramirdor opened on Oct 2, 2026
  4