Pular para o conteúdo
Voltar aos benchmarks

Execução 20261015T171252Z-suite-strd-scripted-d8a322

concluída15/10/2026, 14:12scriptedCadeia: íntegra
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

Dados
ConjuntoPapelEndereçosha256 do arquivoLicença
dagent———
dagent———
dagent———
dagent———
dagent———
dagent———
dagent———
dagent———
dagent———
dagent———
dagent———

Por suíte

Números de cada suíte desta execução
SuíteVersãoTarefasTaxa de acerto ± IC 95%Incidentes como falhaTaxa de incidentesFidelidade de implementaçãoFidelidade de replicaçãoConcordância com o caminho de referênciaAcurácia dado T1Cobertura (ferramenta · agente)Métrica nativaLinhas de base (zero · ingênua)TokensCusto
strd0.1.020100% (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

Tarefas desta execução
TarefaSuíteAlvoDivisãoSituaçãoPontuaçãoDecidida porTentativas
strd.filipstrdtoolpublicpassou1—1
strd.filip.explicit_constantstrdtoolpublicpassou1—1
strd.longleystrdtoolpublicpassou1—1
strd.longley.explicit_constantstrdtoolpublicpassou1—1
strd.noint1strdtoolpublicpassou1—1
strd.noint2strdtoolpublicpassou1—1
strd.norrisstrdtoolpublicpassou1—1
strd.norris.explicit_constantstrdtoolpublicpassou1—1
strd.pontiusstrdtoolpublicpassou1—1
strd.pontius.explicit_constantstrdtoolpublicpassou1—1
strd.wampler1strdtoolpublicpassou1—1
strd.wampler1.explicit_constantstrdtoolpublicpassou1—1
strd.wampler2strdtoolpublicpassou1—1
strd.wampler2.explicit_constantstrdtoolpublicpassou1—1
strd.wampler3strdtoolpublicpassou1—1
strd.wampler3.explicit_constantstrdtoolpublicpassou1—1
strd.wampler4strdtoolpublicpassou1—1
strd.wampler4.explicit_constantstrdtoolpublicpassou1—1
strd.wampler5strdtoolpublicpassou1—1
strd.wampler5.explicit_constantstrdtoolpublicpassou1—1

Downloads

Pacote inteiro (.zip)
176,5 KB · sha256 0ca6ee033c5931bf0e5752318c40eb80ca22d0c8c3f684570f1a20d3175fe647

O 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

Arquivos principais
ArquivoTamanhosha256
manifest.json7,0 KB7d1b71bdb92c497a8cdf461be5e7cd98faf3f1a4759e7ab8449965dbf6436fee
results.jsonl77,5 KBc9fa0891e790071e5d2a72cedcc2d433d954e8ec887383785d2a11371ffa497e
summary.json1,5 KB45f7e9bcd400563ed9bc8c687357b556dd769f3314d461f875a9a89619a730a7
summary.md417 Bccd36c0dbedf44a5befca86b0a0d57222d2fa080fdee7fc69d3fc2bb20206bd5
README.md4,1 KB0e8f9f6fff7f52b038b5d0b8aa5346fa6a5f09e9c9c73655f69cd0f0fbe4f5d5
verify_bundle.py36,1 KBe529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31
SHA256SUMS7,0 KBab3339433da2b006415b0bdbe97efc69b589e5439bfc9fd8520d0757aa14845a
Todos os arquivos do pacote (70)
Todos os arquivos do pacote (70)
ArquivoTamanhosha256
README.md4,1 KB0e8f9f6fff7f52b038b5d0b8aa5346fa6a5f09e9c9c73655f69cd0f0fbe4f5d5
attachments/52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b.json64,0 KB52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b
env/platform.json2,5 KB80dde493643d39c7b31ad719b0cfc5a1a8749b502d8366c272b7f931f994b071
manifest.json7,0 KB7d1b71bdb92c497a8cdf461be5e7cd98faf3f1a4759e7ab8449965dbf6436fee
results.jsonl77,5 KBc9fa0891e790071e5d2a72cedcc2d433d954e8ec887383785d2a11371ffa497e
specs/strd.filip.explicit_constant.json8,5 KB4ab3d37aff357a6d2c6652cdc546ef20c4c940616b8ee97f9f27cc4b6811fdd5
specs/strd.filip.json7,7 KBab3ca35da664d0162602f37e3bb5c6cc1805ae6cf2625e086d6e167e20aba437
specs/strd.longley.explicit_constant.json6,0 KBf790c3dede13ad2bff7a5b4e3f41e492b9fe24edd7111b495963ae421b261074
specs/strd.longley.json5,2 KB74167422f8d2a3a09b5b251ed9c9cd3603c0848fb9e8438f1fe6aaae4805962f
specs/strd.noint1.json2,1 KBf64305c0c4e51a1655e17346532eabab939aa6248216ca5b109befb4be71f8e1
specs/strd.noint2.json2,1 KBe4d21182ca2d9ad9b51ee0da06ea970c62494a5a5a325a9f93f043f209ab0463
specs/strd.norris.explicit_constant.json2,9 KBbe46088fea39d7e9823717a13bc14d4d977bcdd13c9fbef2f6cd00014f756a51
specs/strd.norris.json2,1 KB0eff6a3269ea55864f5044ba806817376138aea0e2903b6ecb8380152ccfed55
specs/strd.pontius.explicit_constant.json3,5 KB86abde91d50f6b8537f361b4a006751e3592cbe4a7241cd765cae65282d6f637
specs/strd.pontius.json2,7 KB4c689b405c789d4cc1374c300c7e4c91f4ef14fa1f0be133432e62fccdada0cf
specs/strd.wampler1.explicit_constant.json5,2 KB9415ab97924840ccbdd7a663ac6a1428f6ff9f33e1b26c2c139914f4de467dbd
specs/strd.wampler1.json4,5 KB1e90674d45edc1bbb586e4e8b358c282ec1fc9125e0236db9e401e6ef2e83aa2
specs/strd.wampler2.explicit_constant.json5,2 KB78538e572fb0fbaf72993dfd7889b397d041782ba43a68b2246132ba6bbdbdb9
specs/strd.wampler2.json4,5 KB5b848b6656a63b1c141ff08eb0ce17a40ceb985fa281298787d4477b616d03ab
specs/strd.wampler3.explicit_constant.json5,3 KB91a3acc74b470b6cf29293916a6653bb2cdcc47263f156853161f5334b90c162
specs/strd.wampler3.json4,6 KB6051ce5541976a66623ce690390d97cb3db2f2b59a4ab7a66e6167d6b43b397d
specs/strd.wampler4.explicit_constant.json5,3 KB3f30f6941d21165bf2783499b38b9a4c8f6f07ce8440f9e9e84934a92a06eaa3
specs/strd.wampler4.json4,6 KB2594d7512c0ab3cbfaa08390c7a14d13ca549a973c31b56810d08be4533ee1e7
specs/strd.wampler5.explicit_constant.json5,3 KBafae0c5efc013911c42452b9368348e4ab544469bf0efcb9f62d4932d5e96cf1
specs/strd.wampler5.json4,6 KBbcb3e288eaf998784b65a604568f7baa589f033b5d3da46e7f7f1424fbce3c8d
summary.json1,5 KB45f7e9bcd400563ed9bc8c687357b556dd769f3314d461f875a9a89619a730a7
summary.md417 Bccd36c0dbedf44a5befca86b0a0d57222d2fa080fdee7fc69d3fc2bb20206bd5
tools/registry.json14,3 KB27ebe450c05193ace734f93b9e9cd24a3072c19308bcdb8877b34d71a6d7670b
traces/strd.filip.e1.a1.jsonl15,6 KB02cace27c969b87ebb329ed11f112d6f617cda18a9e293866fe3c7fc21930344
traces/strd.filip.explicit_constant.e1.a1.jsonl17,0 KB6c8f68ffd17bcec31ddd4110080dbd6fdc7127f0e549d34d5d33b7e25b2b67d4
traces/strd.longley.e1.a1.jsonl10,0 KB3b81c6dae4f7f2350e98a7293a961cf79991c09f3f31e5fa74d9cabba8958640
traces/strd.longley.explicit_constant.e1.a1.jsonl11,4 KB0a164025ac0a42ba06005b00e93096d9348b1205fa38f5f30a16bde27a348959
traces/strd.noint1.e1.a1.jsonl3,1 KB283dafb57b91e61b19d3c67492fa72a089e7f621d290ae341de73f24a8de20f1
traces/strd.noint2.e1.a1.jsonl3,1 KB10d7afe3b0ae821bc51b9caae5bff2a97bf6eac372538aeed6882321f8fc2160
traces/strd.norris.e1.a1.jsonl3,2 KB7f8f688537389bdcb94f133732558b45cb87a14ec4b156f28af4b56bbe8394ea
traces/strd.norris.explicit_constant.e1.a1.jsonl4,5 KB260580df85113a2a07430dc372cf60744c1adba0a0091693653de2234e8b8f6b
traces/strd.pontius.e1.a1.jsonl4,7 KBdaa1275db75e1e4ac4c8a0a78e43c2893bb57cd85b29abd838a404edb6d3c53e
traces/strd.pontius.explicit_constant.e1.a1.jsonl6,0 KB357ca439db67eae7ca808777a9f7a1cd5954feb629674bcb622f6b146adbded0
traces/strd.wampler1.e1.a1.jsonl8,0 KBda085fc5003ab0741dc54f6dcda80a327056f002e23304fc5efc7573a356af33
traces/strd.wampler1.explicit_constant.e1.a1.jsonl9,3 KBee8f9ce22ca413ffe4fdcad9059edce0d5a107ec1f47ed5387c147dcbfcd00fb
traces/strd.wampler2.e1.a1.jsonl8,8 KBd4b1303597306228d48af44363f86d6e01f562bf6d954d196f79371606afe85e
traces/strd.wampler2.explicit_constant.e1.a1.jsonl10,2 KB00024dd5d63a19539b9cad1a974620501eeb5cf733b51d15993aaa0fae4f40ab
traces/strd.wampler3.e1.a1.jsonl8,3 KBac60b9322182f71c935c4c018f8650791eec16ceeebb6da65fa411a076ae3aa2
traces/strd.wampler3.explicit_constant.e1.a1.jsonl9,6 KBa0e4727b3d4828fdc85fa8215edc708c15f8750f6f00b7151817a268a315be6e
traces/strd.wampler4.e1.a1.jsonl8,3 KB3a34413e527d593b0fc12948d3c754c7363f35fa62b97872ed94318d7f5f757c
traces/strd.wampler4.explicit_constant.e1.a1.jsonl9,6 KB083478ded2e0c5ddc2c8346c8a786dc4fe5ba8fa5b7f31d5f38b1728db0508ac
traces/strd.wampler5.e1.a1.jsonl8,3 KBd42b83eea22a287af896a60875957f091a7b0cf0c0c0829fb334621e76ea5eb5
traces/strd.wampler5.explicit_constant.e1.a1.jsonl9,6 KBd3d9c9736842f99d64ec65e12ebf3770231161621ce330f38c59ff18b7c667a7
trajectories/strd.filip.e1.a1.jsonl26,5 KBe7996abd169ada9b051ba414ae546a69a85d1b93af39ffcec4959ddfc47dd5f8
trajectories/strd.filip.explicit_constant.e1.a1.jsonl29,3 KB255a3f8a9a78df6d45abe8467f7816e104c85862a6102b535309d80fa2ca032e
trajectories/strd.longley.e1.a1.jsonl16,7 KBa55705c4e8e300f0caf6d32877cc38f75b07ffc05cb58db6e944c23dfa3a6a6f
trajectories/strd.longley.explicit_constant.e1.a1.jsonl19,3 KB529716a37adc34a1110f92eb0ad552b323829955ef1494caf259d67968e45cad
trajectories/strd.noint1.e1.a1.jsonl5,0 KBc3e9111d96a9e2604e3ff38e25d083d1b18c3d429227c813bfb9b0b32955c5f0
trajectories/strd.noint2.e1.a1.jsonl5,0 KB0213714a869674f2f9dc4ba217f6e1d2aebf34a6ebf8ea17b936ede5b465a038
trajectories/strd.norris.e1.a1.jsonl5,2 KB13270a68c931dc92010e8248382bdb53a53e02061e54c88f874a76a10dd0f340
trajectories/strd.norris.explicit_constant.e1.a1.jsonl7,5 KB6a1f79906d7a3e6745bdefa50657dfc40a7d4fbd14b6bc418d6416422106165e
trajectories/strd.pontius.e1.a1.jsonl7,6 KBa2e12c822569ec9733ba06061dbecf483041b97914bcebc419d70f847f5b3aa9
trajectories/strd.pontius.explicit_constant.e1.a1.jsonl10,0 KBf789e405799b44db35fdf3355a567083991b451564c11e104666785f865c1597
trajectories/strd.wampler1.e1.a1.jsonl13,6 KB6e8a87452ee938e4eab1e7aed666e8ac8537530cb8117cc7e56cc01bef5a3b5a
trajectories/strd.wampler1.explicit_constant.e1.a1.jsonl16,1 KB52048d24035db2ebf7a0bc6337dd7a9cf6575d3226da27aef2df3acf30c9f14e
trajectories/strd.wampler2.e1.a1.jsonl14,4 KB8385528517bf3d53fd689809e6e0ad074352d7a2e7abc27ab8255901eedeab41
trajectories/strd.wampler2.explicit_constant.e1.a1.jsonl17,0 KB5b00764142000314f0118320e5c16ee2d4152719f9d973ffcd20d62cb41fce06
trajectories/strd.wampler3.e1.a1.jsonl14,0 KBc45c6d1099fb0d146c0e0719a7dc4d3b412c0e4c3b4ba7c128c2337268264070
trajectories/strd.wampler3.explicit_constant.e1.a1.jsonl16,5 KB16ca1324912403ad79793762fcca345c4fca5c1c511f996f2825deb5598952fc
trajectories/strd.wampler4.e1.a1.jsonl14,0 KB808d5a25b3cbcc2993e763b2abdc880ecff9d2677db4ca89f3930d75a5be5e0a
trajectories/strd.wampler4.explicit_constant.e1.a1.jsonl16,5 KB6922b2538af518f1a63834e5b6c9e41eb0b0931e718afbfcd026032102ce5d3f
trajectories/strd.wampler5.e1.a1.jsonl14,0 KB84d4c72b2315ac20b45cf9f017d40516b51c2b82496c0b1145e15c1a572541e2
trajectories/strd.wampler5.explicit_constant.e1.a1.jsonl16,5 KB81486d1bfa95ab7d6dcc704a52c57bcbcb294b5af6d919db423187d52d70f191
verify_bundle.py36,1 KBe529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31
SHA256SUMS7,0 KBab3339433da2b006415b0bdbe97efc69b589e5439bfc9fd8520d0757aa14845a

Eventos do registro

Verifique você mesmo

Resumo da execução
ab3339433da2b006415b0bdbe97efc69b589e5439bfc9fd8520d0757aa14845a
sha256 do arquivo SHA256SUMS; deve ser igual ao run_digest do evento final do registro.

Qualquer pessoa, sem o repositório

  1. Baixe o pacote inteiro e descompacte.
  2. 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.