whatmodel.sh / decision / xor (DecisionBench 679decd4)

xor (DecisionBench 679decd4)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

xor (DecisionBench 679decd4) is an open-weights decision model from juspay. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: juspay/xor, revision 679decd4c669e5c37f4ac29dbd9957997424c876; decision-model; adapter xor-serving-systemone-v1; probability source forward_reverse_option_letter_logprobs_calibrated_v1. Kept separate from newer or unpinned Decision Index recipes; standard prompt, not compact. No unverified runtime or OpenRouter price imported. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.

Model information sources

· Weights licence ↗

59.4±1.7#117 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of xor (DecisionBench 679decd4), out of 357 with a score.

#modelscorewhereRAMreleased
116Eikos-27B-FP8 Qwen3.8-27B LoRA caiovicentino159±1model files
117JADE theunnecessarythings59±1model files2026-10-01
118xor (DecisionBench 679decd4) juspay59±2model files
119gpt-5.6-luna (DecisionBench openrout) OpenAI59±2comparison only2026-07-09
120simplejev-qwen3.8-27b (DecisionBench 1d4bf0f2) featherless-ai59±2model files

see all decision models · find the ones that fit your machine

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #31 of 114 · 99% of its score · 27 tests

Beats d1.1 (hosted), Mercury Decide (free endpoint), vLLM-SR d3-flash (9B) here, though they rank higher overall. Trails StartLux-Decision v1.1 2B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted62.7% ✎▂▁▂▃▄▃▁▁▂█▇▄ beats 46/56medium · avg 51%▇▇▇▇▇▇▇▇ 21%at its level
DecisionBench v1 · routing (all-request accuracy) submitted74.0% ✎▁▁▁▁▂▂▁▁▁▁▃█ beats 39/56medium · avg 64%▇▇▇▇▇ 13%sharp
DecisionBench v1 · navigation (all-request accuracy) submitted70.0% ✎▁▁·▃▁▁▁▁▁▁▃█ beats 35/56medium · avg 58%▇▇▇▇ 10%sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted51.0% ✎▃▂▁▂▂▂▄▁▃▆██ beats 54/56medium · avg 39%▇▇▇▇ 10%at its level
DecisionBench v1 · verification (all-request accuracy) submitted60.0% ✎▁▁▅▁▃▂▂▁▁▇▇█ beats 36/56medium · avg 56%▇▇▇ 6.6%blunt · at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted57.0% ✎▂▂·▁▂▄▃▆▄█▁▁ beats 52/56medium · avg 46%▇▇ 5.5%at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted51.4% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 45/56medium · avg 45%▇▇ 4.6%at its level
DecisionBench v1 · triage (all-request accuracy) submitted87.0% ✎▁·▁·▂▃▄▃▂█▄▂ beats 46/56easy · avg 78%▇▇ 3.9%sharp
19 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · completion assessment (all-request accuracy) submitted93.0% ✎▁▁▂▃▄·▂▁▁▆█▂ beats 45/56very easy · avg 86%▇ 3.4%sharp · maxed out
DecisionBench v1 · content classification (all-request accuracy) submitted79.0% ✎▁····▁▁▁▁▁▁█ beats 35/56easy · avg 73%▇ 3.0%typical
DecisionBench v1 · review scoring (all-request accuracy) submitted57.0% ✎▁······▂▃▅▇█ beats 37/56medium · avg 52%▇ 3.0%at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted95.6% ✎▃▃▂·▁▁▁▁▁▁█▅ beats 54/56very easy · avg 86%▇ 2.7%sharp · maxed out · noisy
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted23.0% ✎▁▁·▁▁▂▃▂▃▁▁█ beats 26/56medium · avg 35%▇ 2.5%at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted20.0% ✎▁▁·▁▁▁▃▁▃▁▁█ beats 26/56hard · avg 29%▇ 2.4%at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted73.0% ✎▁▁·▁▂▂▁▃▃█▇▃ beats 54/56medium · avg 62%▇ 2.0%blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted66.1% ✎▂·▁▁▆█▅▃▃▂▁▁ beats 45/56medium · avg 52%▇ 1.3%at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted84.6% ✎█▄▃▁▁▃▂▃▁·▁▁ beats 53/56easy · avg 66%▇ 0.8%blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted87.7% ✎█▁▂▁▁▁▁▁▂▅▁▁ beats 47/56easy · avg 74%▇ 0.7%noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted63.2% ✎▁▁▁▂▆▃▃█···▁ beats 48/56medium · avg 52%▇ 0.6%blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted95.0% ✎▂·····▆█▂▂▄▇ beats 42/56easy · avg 77%▇ 0.4%noisy
DecisionBench v1 · document classification (all-request accuracy) submitted11.0% ✎▂▁·▂▁▁▁▄▁▂▂█ beats 20/56hard · avg 21%▇ 0.4%blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted91.0% ✎▁·▁▁·▁▁█▂▃█▃ beats 56/56easy · avg 71%▇ 0.3%blunt · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted99.0% ✎▁····▃▅▃▂▂·█ beats 40/56easy · avg 82%▇ 0.2%noisy
DecisionBench v1 · context management (all-request accuracy) submitted87.0% ✎▁·····▁▇▆▁█▃ beats 36/56easy · avg 73%▇ 0.2%blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted50.6% ✎▁·▁▄▇▄▅▄▂▁▄█ beats 26/56easy · avg 66%▇ 0.2%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted49.3% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 22/56easy · avg 68%▇ 0.1%blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted0.0% ✎█▁···▁·▂▆▅▂▂ beats 4/56medium · avg 42%▇ 0.0%blunt · at its level · noisy

$ where to run it

Download model files ↗
Published model files verified. This is the revision recorded by the benchmark. A local run command and hardware requirements have not been verified for this entry. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/juspay ↗

$ how the score was worked out · Hanno Labs DecisionBench v1 r… 99%

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

sourceresultsshare of the scorelicence
Hanno Labs DecisionBench v1 reviewed results · submitted; independent execution unverified27CC0 1.0
prior · pull toward the middle
weighted average= 59.4

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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