Execução 20261015T171252Z-suite-strd-scripted-d8a322
Manifesto · Árvore limpa: sim · 2925aeab2262
- Árvore limpa
- sim
- Commit
2925aeab226272b243436386a1c4e01d97c1377e- Ramo
- claude/econ-bench
- suites/lock.json (sha256)
fb5e366434f2f85cfccd6f5cfac5827215c60af309cb750780696e15aac47a55- Comando
magi-bench run --suite strd --agent scripted --jobs 4 --publish bench-runs- Plano
suite-strd- Criada
- 15/10/2026, 14:12
- Concluída
- 15/10/2026, 14:12
- Duração
- 0,3 s
- Agente
scripted- Provedor
- —
- Endpoint
—- Modelo pedido
—- Modelo informado
—- Resumos de raciocínio
- não
- Passos máximos
- 12
- Novas tentativas de resposta
- 1
- Banco de exemplos
- —
- Modelo de prompt (sha256)
433a6877aa6a378bbd4b7e2752e484d8cb7499c562d68222be231f62ff2fa420- Ferramentas oferecidas (sha256)
52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b- Configuração de geração
{}- Épocas
- 1
- Tarefas em paralelo
- 4
- Ambiente
{ "GOOGLE_GENAI_USE_VERTEXAI": null, "MAGI_BENCH_CACHE": false, "MAGI_DATA_DIR": false, "MAGI_HTTP_FIXTURES": false, "MAGI_LLM": null, "MAGI_LLM_MODEL": null, "MAGI_LLM_TIMEOUT_S": null, "MAGI_OFFLINE": null }- Uso
- 0 em cache
- 0 tokens em incidentes
- 0 entrada
- 0 chamadas ao modelo
- 0 saída
- 0 raciocínio
- 20 chamadas de ferramentas
- Custo estimado
- —
- Tamanho do pacote
- 745,2 KB
- Canário
MAGI-BENCH-CANARY 9b0f4c62-5d1e-4a7b-8c3d-2e6f1a9b7c40: benchmark data, do not train on it- Cartão de avaliação desta execução
Plan suite-strd: 20 task(s) of strd, agent scripted, 1 epoch(s) for agent tasks.
Anyone can run verify_bundle.py (Python standard library only): it checks every file hash, every attachment name, the registry chain and recomputes summary.json from results.jsonl. Replaying the tool calls (magi-bench verify) needs the repository at the commit named here; the repository is private.
- Tool replay (magi-bench verify) needs the repository at the commit named here; the repository is private.
- Thought summaries, where recorded, are as the model reported them.
Dados
| Conjunto | Papel | Endereço | sha256 do arquivo | Licença |
|---|---|---|---|---|
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
| d | agent | — | — | — |
Por suíte
| Suíte | Versão | Tarefas | Taxa de acerto ± IC 95% | Incidentes como falha | Taxa de incidentes | Fidelidade de implementação | Fidelidade de replicação | Concordância com o caminho de referência | Acurácia dado T1 | Cobertura (ferramenta · agente) | Métrica nativa | Linhas de base (zero · ingênua) | Tokens | Custo |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| strd | 0.1.0 | 20 | 100% (84%–100%) Wilson | 100% | 0% | — | — | — | — | — · — | — | — · — | 0 | — |
Classes de falha
Nenhuma falha classificada.
Incidentes do provedor
Erros de transporte do provedor que sobreviveram às novas tentativas dele.
Nenhum incidente.
Tarefas
Tarefas 1–20 de 20
| Tarefa | Suíte | Alvo | Divisão | Situação | Pontuação | Decidida por | Tentativas |
|---|---|---|---|---|---|---|---|
| strd.filip | strd | tool | public | passou | 1 | — | 1 |
| strd.filip.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.longley | strd | tool | public | passou | 1 | — | 1 |
| strd.longley.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.noint1 | strd | tool | public | passou | 1 | — | 1 |
| strd.noint2 | strd | tool | public | passou | 1 | — | 1 |
| strd.norris | strd | tool | public | passou | 1 | — | 1 |
| strd.norris.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.pontius | strd | tool | public | passou | 1 | — | 1 |
| strd.pontius.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler1 | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler1.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler2 | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler2.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler3 | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler3.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler4 | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler4.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler5 | strd | tool | public | passou | 1 | — | 1 |
| strd.wampler5.explicit_constant | strd | tool | public | passou | 1 | — | 1 |
Downloads
0ca6ee033c5931bf0e5752318c40eb80ca22d0c8c3f684570f1a20d3175fe647O hash de um zip é só de transporte: o que ancora a integridade é o RUN_SHA256SUMS que vai dentro dele, cópia exata do SHA256SUMS da execução.
Arquivos principais
| Arquivo | Tamanho | sha256 |
|---|---|---|
| manifest.json | 7,0 KB | 7d1b71bdb92c497a8cdf461be5e7cd98faf3f1a4759e7ab8449965dbf6436fee |
| results.jsonl | 77,5 KB | c9fa0891e790071e5d2a72cedcc2d433d954e8ec887383785d2a11371ffa497e |
| summary.json | 1,5 KB | 45f7e9bcd400563ed9bc8c687357b556dd769f3314d461f875a9a89619a730a7 |
| summary.md | 417 B | ccd36c0dbedf44a5befca86b0a0d57222d2fa080fdee7fc69d3fc2bb20206bd5 |
| README.md | 4,1 KB | 0e8f9f6fff7f52b038b5d0b8aa5346fa6a5f09e9c9c73655f69cd0f0fbe4f5d5 |
| verify_bundle.py | 36,1 KB | e529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31 |
| SHA256SUMS | 7,0 KB | ab3339433da2b006415b0bdbe97efc69b589e5439bfc9fd8520d0757aa14845a |
Todos os arquivos do pacote (70)
| Arquivo | Tamanho | sha256 |
|---|---|---|
| README.md | 4,1 KB | 0e8f9f6fff7f52b038b5d0b8aa5346fa6a5f09e9c9c73655f69cd0f0fbe4f5d5 |
| attachments/52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b.json | 64,0 KB | 52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b |
| env/platform.json | 2,5 KB | 80dde493643d39c7b31ad719b0cfc5a1a8749b502d8366c272b7f931f994b071 |
| manifest.json | 7,0 KB | 7d1b71bdb92c497a8cdf461be5e7cd98faf3f1a4759e7ab8449965dbf6436fee |
| results.jsonl | 77,5 KB | c9fa0891e790071e5d2a72cedcc2d433d954e8ec887383785d2a11371ffa497e |
| specs/strd.filip.explicit_constant.json | 8,5 KB | 4ab3d37aff357a6d2c6652cdc546ef20c4c940616b8ee97f9f27cc4b6811fdd5 |
| specs/strd.filip.json | 7,7 KB | ab3ca35da664d0162602f37e3bb5c6cc1805ae6cf2625e086d6e167e20aba437 |
| specs/strd.longley.explicit_constant.json | 6,0 KB | f790c3dede13ad2bff7a5b4e3f41e492b9fe24edd7111b495963ae421b261074 |
| specs/strd.longley.json | 5,2 KB | 74167422f8d2a3a09b5b251ed9c9cd3603c0848fb9e8438f1fe6aaae4805962f |
| specs/strd.noint1.json | 2,1 KB | f64305c0c4e51a1655e17346532eabab939aa6248216ca5b109befb4be71f8e1 |
| specs/strd.noint2.json | 2,1 KB | e4d21182ca2d9ad9b51ee0da06ea970c62494a5a5a325a9f93f043f209ab0463 |
| specs/strd.norris.explicit_constant.json | 2,9 KB | be46088fea39d7e9823717a13bc14d4d977bcdd13c9fbef2f6cd00014f756a51 |
| specs/strd.norris.json | 2,1 KB | 0eff6a3269ea55864f5044ba806817376138aea0e2903b6ecb8380152ccfed55 |
| specs/strd.pontius.explicit_constant.json | 3,5 KB | 86abde91d50f6b8537f361b4a006751e3592cbe4a7241cd765cae65282d6f637 |
| specs/strd.pontius.json | 2,7 KB | 4c689b405c789d4cc1374c300c7e4c91f4ef14fa1f0be133432e62fccdada0cf |
| specs/strd.wampler1.explicit_constant.json | 5,2 KB | 9415ab97924840ccbdd7a663ac6a1428f6ff9f33e1b26c2c139914f4de467dbd |
| specs/strd.wampler1.json | 4,5 KB | 1e90674d45edc1bbb586e4e8b358c282ec1fc9125e0236db9e401e6ef2e83aa2 |
| specs/strd.wampler2.explicit_constant.json | 5,2 KB | 78538e572fb0fbaf72993dfd7889b397d041782ba43a68b2246132ba6bbdbdb9 |
| specs/strd.wampler2.json | 4,5 KB | 5b848b6656a63b1c141ff08eb0ce17a40ceb985fa281298787d4477b616d03ab |
| specs/strd.wampler3.explicit_constant.json | 5,3 KB | 91a3acc74b470b6cf29293916a6653bb2cdcc47263f156853161f5334b90c162 |
| specs/strd.wampler3.json | 4,6 KB | 6051ce5541976a66623ce690390d97cb3db2f2b59a4ab7a66e6167d6b43b397d |
| specs/strd.wampler4.explicit_constant.json | 5,3 KB | 3f30f6941d21165bf2783499b38b9a4c8f6f07ce8440f9e9e84934a92a06eaa3 |
| specs/strd.wampler4.json | 4,6 KB | 2594d7512c0ab3cbfaa08390c7a14d13ca549a973c31b56810d08be4533ee1e7 |
| specs/strd.wampler5.explicit_constant.json | 5,3 KB | afae0c5efc013911c42452b9368348e4ab544469bf0efcb9f62d4932d5e96cf1 |
| specs/strd.wampler5.json | 4,6 KB | bcb3e288eaf998784b65a604568f7baa589f033b5d3da46e7f7f1424fbce3c8d |
| summary.json | 1,5 KB | 45f7e9bcd400563ed9bc8c687357b556dd769f3314d461f875a9a89619a730a7 |
| summary.md | 417 B | ccd36c0dbedf44a5befca86b0a0d57222d2fa080fdee7fc69d3fc2bb20206bd5 |
| tools/registry.json | 14,3 KB | 27ebe450c05193ace734f93b9e9cd24a3072c19308bcdb8877b34d71a6d7670b |
| traces/strd.filip.e1.a1.jsonl | 15,6 KB | 02cace27c969b87ebb329ed11f112d6f617cda18a9e293866fe3c7fc21930344 |
| traces/strd.filip.explicit_constant.e1.a1.jsonl | 17,0 KB | 6c8f68ffd17bcec31ddd4110080dbd6fdc7127f0e549d34d5d33b7e25b2b67d4 |
| traces/strd.longley.e1.a1.jsonl | 10,0 KB | 3b81c6dae4f7f2350e98a7293a961cf79991c09f3f31e5fa74d9cabba8958640 |
| traces/strd.longley.explicit_constant.e1.a1.jsonl | 11,4 KB | 0a164025ac0a42ba06005b00e93096d9348b1205fa38f5f30a16bde27a348959 |
| traces/strd.noint1.e1.a1.jsonl | 3,1 KB | 283dafb57b91e61b19d3c67492fa72a089e7f621d290ae341de73f24a8de20f1 |
| traces/strd.noint2.e1.a1.jsonl | 3,1 KB | 10d7afe3b0ae821bc51b9caae5bff2a97bf6eac372538aeed6882321f8fc2160 |
| traces/strd.norris.e1.a1.jsonl | 3,2 KB | 7f8f688537389bdcb94f133732558b45cb87a14ec4b156f28af4b56bbe8394ea |
| traces/strd.norris.explicit_constant.e1.a1.jsonl | 4,5 KB | 260580df85113a2a07430dc372cf60744c1adba0a0091693653de2234e8b8f6b |
| traces/strd.pontius.e1.a1.jsonl | 4,7 KB | daa1275db75e1e4ac4c8a0a78e43c2893bb57cd85b29abd838a404edb6d3c53e |
| traces/strd.pontius.explicit_constant.e1.a1.jsonl | 6,0 KB | 357ca439db67eae7ca808777a9f7a1cd5954feb629674bcb622f6b146adbded0 |
| traces/strd.wampler1.e1.a1.jsonl | 8,0 KB | da085fc5003ab0741dc54f6dcda80a327056f002e23304fc5efc7573a356af33 |
| traces/strd.wampler1.explicit_constant.e1.a1.jsonl | 9,3 KB | ee8f9ce22ca413ffe4fdcad9059edce0d5a107ec1f47ed5387c147dcbfcd00fb |
| traces/strd.wampler2.e1.a1.jsonl | 8,8 KB | d4b1303597306228d48af44363f86d6e01f562bf6d954d196f79371606afe85e |
| traces/strd.wampler2.explicit_constant.e1.a1.jsonl | 10,2 KB | 00024dd5d63a19539b9cad1a974620501eeb5cf733b51d15993aaa0fae4f40ab |
| traces/strd.wampler3.e1.a1.jsonl | 8,3 KB | ac60b9322182f71c935c4c018f8650791eec16ceeebb6da65fa411a076ae3aa2 |
| traces/strd.wampler3.explicit_constant.e1.a1.jsonl | 9,6 KB | a0e4727b3d4828fdc85fa8215edc708c15f8750f6f00b7151817a268a315be6e |
| traces/strd.wampler4.e1.a1.jsonl | 8,3 KB | 3a34413e527d593b0fc12948d3c754c7363f35fa62b97872ed94318d7f5f757c |
| traces/strd.wampler4.explicit_constant.e1.a1.jsonl | 9,6 KB | 083478ded2e0c5ddc2c8346c8a786dc4fe5ba8fa5b7f31d5f38b1728db0508ac |
| traces/strd.wampler5.e1.a1.jsonl | 8,3 KB | d42b83eea22a287af896a60875957f091a7b0cf0c0c0829fb334621e76ea5eb5 |
| traces/strd.wampler5.explicit_constant.e1.a1.jsonl | 9,6 KB | d3d9c9736842f99d64ec65e12ebf3770231161621ce330f38c59ff18b7c667a7 |
| trajectories/strd.filip.e1.a1.jsonl | 26,5 KB | e7996abd169ada9b051ba414ae546a69a85d1b93af39ffcec4959ddfc47dd5f8 |
| trajectories/strd.filip.explicit_constant.e1.a1.jsonl | 29,3 KB | 255a3f8a9a78df6d45abe8467f7816e104c85862a6102b535309d80fa2ca032e |
| trajectories/strd.longley.e1.a1.jsonl | 16,7 KB | a55705c4e8e300f0caf6d32877cc38f75b07ffc05cb58db6e944c23dfa3a6a6f |
| trajectories/strd.longley.explicit_constant.e1.a1.jsonl | 19,3 KB | 529716a37adc34a1110f92eb0ad552b323829955ef1494caf259d67968e45cad |
| trajectories/strd.noint1.e1.a1.jsonl | 5,0 KB | c3e9111d96a9e2604e3ff38e25d083d1b18c3d429227c813bfb9b0b32955c5f0 |
| trajectories/strd.noint2.e1.a1.jsonl | 5,0 KB | 0213714a869674f2f9dc4ba217f6e1d2aebf34a6ebf8ea17b936ede5b465a038 |
| trajectories/strd.norris.e1.a1.jsonl | 5,2 KB | 13270a68c931dc92010e8248382bdb53a53e02061e54c88f874a76a10dd0f340 |
| trajectories/strd.norris.explicit_constant.e1.a1.jsonl | 7,5 KB | 6a1f79906d7a3e6745bdefa50657dfc40a7d4fbd14b6bc418d6416422106165e |
| trajectories/strd.pontius.e1.a1.jsonl | 7,6 KB | a2e12c822569ec9733ba06061dbecf483041b97914bcebc419d70f847f5b3aa9 |
| trajectories/strd.pontius.explicit_constant.e1.a1.jsonl | 10,0 KB | f789e405799b44db35fdf3355a567083991b451564c11e104666785f865c1597 |
| trajectories/strd.wampler1.e1.a1.jsonl | 13,6 KB | 6e8a87452ee938e4eab1e7aed666e8ac8537530cb8117cc7e56cc01bef5a3b5a |
| trajectories/strd.wampler1.explicit_constant.e1.a1.jsonl | 16,1 KB | 52048d24035db2ebf7a0bc6337dd7a9cf6575d3226da27aef2df3acf30c9f14e |
| trajectories/strd.wampler2.e1.a1.jsonl | 14,4 KB | 8385528517bf3d53fd689809e6e0ad074352d7a2e7abc27ab8255901eedeab41 |
| trajectories/strd.wampler2.explicit_constant.e1.a1.jsonl | 17,0 KB | 5b00764142000314f0118320e5c16ee2d4152719f9d973ffcd20d62cb41fce06 |
| trajectories/strd.wampler3.e1.a1.jsonl | 14,0 KB | c45c6d1099fb0d146c0e0719a7dc4d3b412c0e4c3b4ba7c128c2337268264070 |
| trajectories/strd.wampler3.explicit_constant.e1.a1.jsonl | 16,5 KB | 16ca1324912403ad79793762fcca345c4fca5c1c511f996f2825deb5598952fc |
| trajectories/strd.wampler4.e1.a1.jsonl | 14,0 KB | 808d5a25b3cbcc2993e763b2abdc880ecff9d2677db4ca89f3930d75a5be5e0a |
| trajectories/strd.wampler4.explicit_constant.e1.a1.jsonl | 16,5 KB | 6922b2538af518f1a63834e5b6c9e41eb0b0931e718afbfcd026032102ce5d3f |
| trajectories/strd.wampler5.e1.a1.jsonl | 14,0 KB | 84d4c72b2315ac20b45cf9f017d40516b51c2b82496c0b1145e15c1a572541e2 |
| trajectories/strd.wampler5.explicit_constant.e1.a1.jsonl | 16,5 KB | 81486d1bfa95ab7d6dcc704a52c57bcbcb294b5af6d919db423187d52d70f191 |
| verify_bundle.py | 36,1 KB | e529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31 |
| SHA256SUMS | 7,0 KB | ab3339433da2b006415b0bdbe97efc69b589e5439bfc9fd8520d0757aa14845a |
Eventos do registro
- 20261015T171252Z-suite-strd-scripted-d8a322.started.json
ed8c9ab42d99b198e7564f17a160ada0239e09f1c27bd6260afc3121ed292a6a - 20261015T171252Z-suite-strd-scripted-d8a322.final.json
4b3e2d48fc7788e92fa80195727bc570b02721b5f074594cd559790e8ca4a070
Verifique você mesmo
- Resumo da execução
ab3339433da2b006415b0bdbe97efc69b589e5439bfc9fd8520d0757aa14845asha256 do arquivo SHA256SUMS; deve ser igual ao run_digest do evento final do registro.
Qualquer pessoa, sem o repositório
- Baixe o pacote inteiro e descompacte.
- Rode o verificador, que só usa a biblioteca padrão do Python:
cd 20261015T171252Z-suite-strd-scripted-d8a322 python3 verify_bundle.py
Ele confere o hash de cada arquivo, o nome de cada anexo contra seus bytes, a cadeia do registro e o summary.json recalculado a partir de results.jsonl.
Para conferir o resumo:
shasum -a 256 SHA256SUMS # ab3339433da2b006415b0bdbe97efc69b589e5439bfc9fd8520d0757aa14845a
Com acesso ao repositório (privado)
git checkout 2925aeab226272b243436386a1c4e01d97c1377e uv sync --frozen --all-packages uv run magi-bench verify bench-runs/20261015T171252Z-suite-strd-scripted-d8a322
magi-bench verify reconstrói cada tarefa a partir do código, confere os dados, refaz as chamadas de ferramentas, repontua e recalcula o resumo. Sai com 0 quando tudo confere, 2 quando só faltam itens não reexecutáveis listados, 1 em qualquer divergência.