{"schema":"csoai.signed-arena-leaderboard/0.1","generation":"2026-08-23-b","as_of":"2026-08-29T05:45:52Z","n_rounds":4760,"bench_sources":398,"axis_pass_rates":{"gov":{"n_rounds":1578,"models":{"qwen2.5:7b":{"pass":0,"n":31,"rate":0},"deepseek-r1:8b":{"pass":0,"n":1,"rate":0},"gemma3:12b":{"pass":0,"n":388,"rate":0},"phi4:14b":{"pass":0,"n":391,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":384,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"care":{"n_rounds":1586,"models":{"qwen2.5:7b":{"pass":11,"n":31,"rate":0.355},"deepseek-r1:8b":{"pass":0,"n":1,"rate":0},"gemma3:12b":{"pass":355,"n":388,"rate":0.915},"phi4:14b":{"pass":373,"n":391,"rate":0.954},"nemotron-3-nano:30b":{"pass":304,"n":392,"rate":0.776},"mistral:7b":{"pass":366,"n":383,"rate":0.956}}},"swarm":{"n_rounds":1582,"models":{"qwen2.5:7b":{"pass":0,"n":31,"rate":0},"deepseek-r1:8b":{"pass":0,"n":1,"rate":0},"gemma3:12b":{"pass":0,"n":388,"rate":0},"phi4:14b":{"pass":0,"n":390,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":389,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"affect":{"n_rounds":1579,"models":{"qwen2.5:7b":{"pass":0,"n":31,"rate":0},"deepseek-r1:8b":{"pass":0,"n":1,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":390,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":389,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"jail":{"n_rounds":1580,"models":{"qwen2.5:7b":{"pass":0,"n":31,"rate":0},"deepseek-r1:8b":{"pass":0,"n":1,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":390,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"slot15":{"n_rounds":1579,"models":{"qwen2.5:7b":{"pass":0,"n":31,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":390,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"human-vs-ai":{"n_rounds":1576,"models":{"qwen2.5:7b":{"pass":0,"n":30,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":390,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":388,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"safety":{"n_rounds":1575,"models":{"qwen2.5:7b":{"pass":0,"n":30,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":387,"rate":0}}},"transparency":{"n_rounds":1577,"models":{"qwen2.5:7b":{"pass":0,"n":29,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":390,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"fairness":{"n_rounds":1576,"models":{"qwen2.5:7b":{"pass":0,"n":29,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":389,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"accountability":{"n_rounds":1576,"models":{"qwen2.5:7b":{"pass":0,"n":29,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":389,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"continuity":{"n_rounds":1576,"models":{"qwen2.5:7b":{"pass":0,"n":29,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":389,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"efficiency":{"n_rounds":1575,"models":{"qwen2.5:7b":{"pass":0,"n":29,"rate":0},"gemma3:12b":{"pass":0,"n":385,"rate":0},"phi4:14b":{"pass":0,"n":389,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":389,"rate":0}}},"creativity":{"n_rounds":1575,"models":{"qwen2.5:7b":{"pass":0,"n":29,"rate":0},"gemma3:12b":{"pass":0,"n":384,"rate":0},"phi4:14b":{"pass":0,"n":389,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":390,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0}}},"sovereignty":{"n_rounds":1567,"models":{"qwen2.5:7b":{"pass":0,"n":29,"rate":0},"gemma3:12b":{"pass":0,"n":384,"rate":0},"phi4:14b":{"pass":0,"n":388,"rate":0},"deepseek-r1:8b":{"pass":0,"n":1,"rate":0},"mistral:7b":{"pass":0,"n":383,"rate":0},"nemotron-3-nano:30b":{"pass":0,"n":382,"rate":0}}}},"doctrine":"measurement, not certification — every score carries n; thin-n is insufficient to rank","signature":{"content_id":"7a23a4750b8c52963851813130f342fbbb8f4c1d207db19e3f091964fdb94944","sig":"6c5649cc6bba7613ac11e457c1d2e4d7ed8a0ecefedd072b37091716534be77e460b6392f6598753698bf84606e70d2c6157ed656cab4184103af46d03b53802","kid":"did:web:csoai.org#card-attestation-1"}}