Show HN: JevBench,一个可复现的类型化决策模型基准测试工具
Show HN: JevBench, a reproducible benchmark for typed decision models

原始链接: https://benchmarkheaven.com/jev-models

该数据集展示了 48 种不同模型在五个不同测试类别中的 JevBench 性能排名。结果显示出显著的差异性,许多模型的排名与其 JevBench 总分相比存在波动。 **主要观察结果:** * **顶尖表现:** Jev 1.13.0、SemIf 和 djev 等模型表现稳定,排名靠前,在所评估的类别中经常位居前列。 * **性能差距:** 性能差距巨大,从得分较高的模型(70 多分和 80 多分)到排名垫底的模型(如 Certo v1,得分接近零)不等。 * **不一致性:** 数据中一个值得注意的反复出现的现象是,各分类别的排名经常与 JevBench 总分不同,这表明某些模型无论总排名如何,在特定的测试环境下可能表现优异或不佳。 * **底层梯队:** 榜单末尾是一些专用模型和重排序模型(如 GLiNER、Mixedbread、BAAI),它们在这些特定基准测试中的表现微乎其微。 总体而言,该数据突显了模型能力的多样化格局,其性能高度依赖于具体的评估标准。

**JevBench** 是一款全新的、可复现的基准测试工具,旨在评估“Jev 类”模型。这类模型属于类型化决策模型,输出的是结构化的选择和概率,而非原始文本。与传统大语言模型相比,它们在保持高智能水平的同时,更具速度优势且成本效益更高。 该基准测试提供了一套统一的评分系统(v1.3),平衡了四个关键指标:智能水平(经机会修正)、校准度、速度和成本。用户可以根据自身需求自定义这些指标的权重。完整的评估包含 534 项英语决策任务。 目前的排行榜显示,*Jev* 以 74.4 分位居榜首,*SemIf* 和 *djev* 紧随其后。 该项目完全开源(MIT 许可证),并公开了工具产物、评分代码和任务结果。尽管开发者指出了目前的局限性(例如仅限英语,且延迟测量依赖于单台德国服务器),但该工具已正式上线,并提供两个无需注册的演示页面,供用户亲自测试性能。 **资源:** * **GitHub:** [fstandhartinger/jevbench](https://github.com/fstandhartinger/jevbench) * **演示:** [who-is-right](https://who-is-right.app.mintapis.com) 和 [is-it-ai-slop](https://is-it-ai-slop.app.mintapis.com)
相关文章

原文
Jev 1.13.0#1 74.4#3 71.8 (rank differs from the JevBench Score)#2 77.1 (rank differs from the JevBench Score)#4 76.2 (rank differs from the JevBench Score)#9 63.1 (rank differs from the JevBench Score)SemIf#2 73.1#2 73.3#3 75.5 (rank differs from the JevBench Score)#2 77.3#4 67.4 (rank differs from the JevBench Score)djev#3 73.0#1 75.8 (rank differs from the JevBench Score)#1 78.5 (rank differs from the JevBench Score)#1 81.7 (rank differs from the JevBench Score)#3 67.9Winnow-12B Q8#4 71.2#4 71.0#4 75.2#5 75.3 (rank differs from the JevBench Score)#10 63.1 (rank differs from the JevBench Score)reflex 4B#5 70.3#6 68.8 (rank differs from the JevBench Score)#5 73.1#17 68.4 (rank differs from the JevBench Score)#5 65.0jqv#6 68.6#14 65.5 (rank differs from the JevBench Score)#9 70.7 (rank differs from the JevBench Score)#14 69.0 (rank differs from the JevBench Score)#14 57.6 (rank differs from the JevBench Score)decision-machine-1#7 68.3#9 67.6 (rank differs from the JevBench Score)#22 65.4 (rank differs from the JevBench Score)#3 76.8 (rank differs from the JevBench Score)#11 61.7 (rank differs from the JevBench Score)decider-35b-a3b#8 67.6#13 66.3 (rank differs from the JevBench Score)#8 71.3#10 71.7 (rank differs from the JevBench Score)#18 56.9 (rank differs from the JevBench Score)open-alternative-jev#9 67.0#7 68.3 (rank differs from the JevBench Score)#17 66.6 (rank differs from the JevBench Score)#6 74.0 (rank differs from the JevBench Score)#8 64.7 (rank differs from the JevBench Score)system-one-open#10 66.6#5 70.3 (rank differs from the JevBench Score)#11 70.0 (rank differs from the JevBench Score)#9 72.9 (rank differs from the JevBench Score)#2 68.0 (rank differs from the JevBench Score)OpenJev#11 66.4#11 66.9#7 71.6 (rank differs from the JevBench Score)#8 73.0 (rank differs from the JevBench Score)#15 57.3 (rank differs from the JevBench Score)SimpleJev Qwen3.8-27B#12 66.3#18 62.0 (rank differs from the JevBench Score)#10 70.2 (rank differs from the JevBench Score)#24 65.5 (rank differs from the JevBench Score)#22 51.8 (rank differs from the JevBench Score)ZeroEntropy zerank-2#13 66.0#15 62.8 (rank differs from the JevBench Score)#29 62.9 (rank differs from the JevBench Score)#15 68.8 (rank differs from the JevBench Score)#16 57.2 (rank differs from the JevBench Score)GPT-5.6 Luna#14 65.9#23 59.5 (rank differs from the JevBench Score)#6 71.8 (rank differs from the JevBench Score)#23 66.1 (rank differs from the JevBench Score)#30 44.3 (rank differs from the JevBench Score)openjev-sglang#15 65.3#19 61.7 (rank differs from the JevBench Score)#12 69.6 (rank differs from the JevBench Score)#18 67.4 (rank differs from the JevBench Score)#24 50.0 (rank differs from the JevBench Score)Qwen3-Reranker-4B#16 63.8#16 62.8#27 63.3 (rank differs from the JevBench Score)#16 68.7#17 56.9 (rank differs from the JevBench Score)reflex-27b#17 63.3#26 57.2 (rank differs from the JevBench Score)#16 67.2 (rank differs from the JevBench Score)#28 61.1 (rank differs from the JevBench Score)#27 45.5 (rank differs from the JevBench Score)LitJev#18 62.7#28 57.0 (rank differs from the JevBench Score)#19 66.0 (rank differs from the JevBench Score)#29 60.7 (rank differs from the JevBench Score)#26 46.1 (rank differs from the JevBench Score)kev 0.6B#19 62.5#12 66.8 (rank differs from the JevBench Score)#30 60.4 (rank differs from the JevBench Score)#13 70.2 (rank differs from the JevBench Score)#1 70.4 (rank differs from the JevBench Score)SimpleJev Qwen3.6-35B-A3B#20 62.5#21 61.0 (rank differs from the JevBench Score)#14 67.8 (rank differs from the JevBench Score)#21 66.3 (rank differs from the JevBench Score)#23 50.6 (rank differs from the JevBench Score)djev#21 62.4#30 54.6 (rank differs from the JevBench Score)#25 63.9 (rank differs from the JevBench Score)#27 62.1 (rank differs from the JevBench Score)#34 41.1 (rank differs from the JevBench Score)jev-local#22 61.8#22 59.6#26 63.9 (rank differs from the JevBench Score)#26 63.3 (rank differs from the JevBench Score)#21 52.5 (rank differs from the JevBench Score)decider-2b#23 61.7#8 67.7 (rank differs from the JevBench Score)#23 65.1#7 73.5 (rank differs from the JevBench Score)#7 64.9 (rank differs from the JevBench Score)Bespoke Nimble 9B#24 60.5#24 58.9#20 65.9 (rank differs from the JevBench Score)#22 66.2 (rank differs from the JevBench Score)#25 47.0 (rank differs from the JevBench Score)Gemini 3.1 Flash-Lite#25 60.1#25 57.6#15 67.5 (rank differs from the JevBench Score)#20 66.3 (rank differs from the JevBench Score)#32 42.8 (rank differs from the JevBench Score)OpenJev#26 60.0#27 57.1 (rank differs from the JevBench Score)#13 67.9 (rank differs from the JevBench Score)#25 64.0 (rank differs from the JevBench Score)#31 42.8 (rank differs from the JevBench Score)kev 4B#27 59.7#10 67.2 (rank differs from the JevBench Score)#18 66.2 (rank differs from the JevBench Score)#12 70.5 (rank differs from the JevBench Score)#6 65.0 (rank differs from the JevBench Score)DeepSeek V4.1 Flash#28 57.5#34 48.4 (rank differs from the JevBench Score)#28 63.2#33 56.6 (rank differs from the JevBench Score)#40 31.7 (rank differs from the JevBench Score)kev 8B#29 56.4#20 61.2 (rank differs from the JevBench Score)#24 64.3 (rank differs from the JevBench Score)#19 66.3 (rank differs from the JevBench Score)#19 53.6 (rank differs from the JevBench Score)Open-Jev 9B#30 55.0#32 52.4 (rank differs from the JevBench Score)#31 59.3 (rank differs from the JevBench Score)#30 59.5#35 40.9 (rank differs from the JevBench Score)system-one#31 54.8#17 62.6 (rank differs from the JevBench Score)#21 65.6 (rank differs from the JevBench Score)#11 70.6 (rank differs from the JevBench Score)#20 53.1 (rank differs from the JevBench Score)jeff#32 54.4#31 53.6 (rank differs from the JevBench Score)#33 48.2 (rank differs from the JevBench Score)#34 54.5 (rank differs from the JevBench Score)#13 58.7 (rank differs from the JevBench Score)Laya#33 54.4#29 55.0 (rank differs from the JevBench Score)#34 47.7 (rank differs from the JevBench Score)#32 56.8 (rank differs from the JevBench Score)#12 61.4 (rank differs from the JevBench Score)Open-Jev 2B#34 51.3#33 50.1 (rank differs from the JevBench Score)#32 54.2 (rank differs from the JevBench Score)#31 58.4 (rank differs from the JevBench Score)#37 39.8 (rank differs from the JevBench Score)OpenDecision#35 40.6#35 41.7#35 35.2#35 46.0#28 44.9 (rank differs from the JevBench Score)openJev Verdict 1.4#36 38.9#37 37.4 (rank differs from the JevBench Score)#38 30.7 (rank differs from the JevBench Score)#37 40.8 (rank differs from the JevBench Score)#33 41.6 (rank differs from the JevBench Score)openJev Verdict#37 38.1#36 40.1 (rank differs from the JevBench Score)#36 33.3 (rank differs from the JevBench Score)#36 43.3 (rank differs from the JevBench Score)#29 44.7 (rank differs from the JevBench Score)kev 0.5B#38 33.2#39 35.4 (rank differs from the JevBench Score)#39 29.4 (rank differs from the JevBench Score)#38 38.9#38 38.7GLiNER2 large#39 29.6#38 36.5 (rank differs from the JevBench Score)#37 31.8 (rank differs from the JevBench Score)#39 37.8#36 40.5 (rank differs from the JevBench Score)smalljev semantic-v9#40 27.4#41 26.9 (rank differs from the JevBench Score)#41 22.6 (rank differs from the JevBench Score)#41 31.4 (rank differs from the JevBench Score)#41 27.6 (rank differs from the JevBench Score)GLiNER2#41 24.0#40 30.3 (rank differs from the JevBench Score)#40 24.6 (rank differs from the JevBench Score)#40 32.6 (rank differs from the JevBench Score)#39 34.6 (rank differs from the JevBench Score)open-jev-deberta-v3-large#42 23.1#42 21.9#42 17.8#42 23.7#42 24.9GLiNER2.5 multi#43 16.6#43 16.4#43 12.6#43 18.0#43 19.5GLiNER2.5 small#44 13.8#44 14.4#44 10.6#44 16.5#44 16.9Mixedbread mxbai-rerank-base-v2#45 0.8#45 0.6#45 0.3#45 0.9#45 0.8BAAI bge-reranker-v2-m3#46 0.7#46 0.5#46 0.3#46 0.8#46 0.7Alibaba GTE Reranker ModernBERT-base#47 0.3#47 0.3#47 0.1#47 0.4#47 0.4Certo v1#48 0.0#48 0.0#48 0.0#48 0.0#48 0.0
联系我们 contact @ memedata.com