Entries 49 to 64 of 64, in the hub's default order. The introduction is on page 1.
Showing 49 to 64 of 64
A leaderboard that runs Jev and 54 open System One models and clones through the same 120,000-question suite on one RTX PRO 6000, scoring accuracy and calibration. Jev leads the 0.2 edition at 51.67 on a chance-corrected scale, with AutoJev-27B close behind at 50.94.
apolinario (poli) (@multimodalart)43k viewsOpenJev Decision Index: Jev against 50+ open decision models on huggingface.co
A maze demo comparing decision latency: local Laya on a base M5 responds at a 19ms median, versus roughly 300ms from Jev's cloud API for the same task.
Video benchmark where Jev wins outright as a cloud model, while a self-built JAX model ties with Laya-MLX among the local, on-device options.
Tom Siwik (@tomhacks)11k viewsOpenJev, Laya-MLX and a Custom JAX Build on a Local Game Benchmark on x.com
Custom Snake benchmark comparing Jev over the API against locally run Laya-MLX and Kev-4B: Jev had zero deaths, Kev died twice at about 175ms latency, and Laya died early despite roughly 33ms latency.
Tobias Wupperfeld (@tobiaswup)3.1k viewsOpenHome-Made Snake Benchmark: Jev vs Laya-MLX vs Kev-4B on x.com
21-minute video scoring seven open-source Jev-family models on JevBench, ending with Laya, and noting write-ups conflate the multilingual 322M checkpoint's 1k context with the 421M English checkpoint's 512.
Ran 996 questions adapted from Berkeley CS 70 finals through Jev, SemIf and Laya under the same grading. Jev scored 83.7 percent, SemIf 61.6 percent, and Laya 31.2 percent, close to the roughly 30 percent expected from random guessing.
Tested Jev against a local MLX build of Laya in zero-shot mode on 40 English and Thai support tickets. Jev scored 90 to 100 percent accuracy, Laya scored 30 to 80 percent, though Laya ran faster.
An independent benchmark testing Jev against Laya on the same 140 labels, checking whether each engine's own feedback loop finds a hidden labeling factor, and fine-tuning Laya on the same data to compare results.
Runs early-access Jev over 24 Norwegian submissions to the 2022 hearing on resource rent tax for salmon farming, reporting agreement with a frontier model's labels, calibration, cost and latency. Compared against DeepSeek V4.1 Flash with and without reasoning.
16,000 calls comparing Jev with gpt-5.4-mini and gpt-5.6-luna on four public datasets, then on a few thousand real pipeline decisions. Covers where it wins, where it breaks, and how to use it.
Measures one direct Jev call per row against 12 to 14 Jev-scored dimensions fed into a locally trained linear model, across three classification tasks. Decomposition lifted Japanese NLI from 0.837 to 0.908 but was about 25 times worse on false positives against hard benign input, and the whole run cost $1.43 over 5,477 test rows.
The author ran Jev through his LLM Chess benchmark, where a model repeatedly picks from a list of legal moves rather than generating free text. Jev's win rate against the random-move baseline landed close to several reasoning models, despite Jev not being built to reason.
Near Here compares Jev with Mistral Small 4 and Gemini 3.5 Flash-Lite at rejecting unsuitable local event listings, each with its own tuned prompt. Jev scored 48 of 50 on the main test set at a median 0.58 seconds, and the post includes token counts, cost per decision and a downloadable comparison PDF.
Verifies that each citation in generated text is actually supported by the cited source.
Benchmark Heaven's own leaderboard for Jev-class decision models, unrelated to the dhruvmehra/jevbench repo, ranking 106 of 112 systems on 1,624 choice, score and noul decisions each in release v1.5.4. Jev 1.13.0 leads on capability at 80.0, while on the four-axis composite that adds speed and cost, Cygnet and Winnow-12B Q8 tie first and Jev is third.
Official site publishing TypeSafe's four workflow evals (security incidents, agent-trace observability, invoice processing, customer service) with per-model accuracy, cost and latency, including Jev alongside Claude, GPT and Gemini models.
Nothing matches those filters
Clear a filter to widen the search, or send us the thing you were looking for.
