Files
maka/docs/eval/terminal-bench-2.1-deepseek-v4-flash-four-arm.csv
T
agent-radar 7be535059e
Dependency audit / audit (push) Canceled after 0s
CI / plan (push) Canceled after 0s
Gitoxide helper admission / macos-latest (push) Canceled after 0s
Gitoxide helper admission / ubuntu-latest (push) Canceled after 0s
Gitoxide helper admission / windows-latest (push) Canceled after 0s
Runtime Host peer admission / quality (push) Canceled after 0s
Windows recovery / windows_recovery (push) Canceled after 0s
CI / heavy (push) Canceled after 0s
CI / test (push) Canceled after 0s
源码快照 @ 2026-09-01 (source-only, 剔除非源码素材)
2026-09-01 19:05:14 +08:00

6.4 KiB

1task_idmakacodexclaude-codereasonixmaka_failure_classcodex_failure_classclaude-code_failure_classreasonix_failure_class
2adaptive-rejection-samplerpassedpassedfailedunscoredbudget_exhaustedinfra_failed
3bn-fit-modifypassedpassedfailedpassedverification_failed
4break-filter-js-from-htmlpassedpassedpassedpassed
5build-cython-extpassedpassedpassedpassed
6build-pmarspassedpassedpassedpassed
7build-pov-raypassedpassedpassedpassed
8caffe-cifar-10passedpassedpassedpassed
9cancel-async-tasksfailedpassedfailedpassedverification_failedbudget_exhausted
10chess-best-movefailedfailedfailedfailedverification_failedbudget_exhaustedbudget_exhaustedbudget_exhausted
11circuit-fibsqrtpassedpassedpassedfailedverification_failed
12cobol-modernizationpassedpassedpassedpassed
13code-from-imagefailedpassedfailedpassedbudget_exhaustedbudget_exhausted
14compile-compcertpassedpassedpassedpassed
15configure-git-webserverfailedpassedpassedpassedverification_failed
16constraints-schedulingpassedpassedpassedpassed
17count-dataset-tokenspassedpassedpassedfailedverification_failed
18crack-7z-hashpassedpassedpassedfailedbudget_exhausted
19custom-memory-heap-crashpassedpassedpassedpassed
20db-wal-recoverypassedpassedfailedpassedbudget_exhausted
21distribution-searchpassedpassedpassedpassed
22dna-assemblyfailedpassedfailedfailedverification_failedbudget_exhaustedverification_failed
23dna-insertfailedpassedpassedfailedverification_failedverification_failed
24extract-elfpassedfailedfailedfailedverification_failedverification_failedverification_failed
25extract-moves-from-videofailedfailedfailedfailedbudget_exhaustedbudget_exhaustedbudget_exhaustedbudget_exhausted
26feal-differential-cryptanalysispassedfailedpassedpassedverification_failed
27feal-linear-cryptanalysispassedpassedpassedpassed
28filter-js-from-htmlfailedfailedfailedfailedverification_failedverification_failedverification_failedverification_failed
29financial-document-processorpassedpassedpassedpassed
30fix-code-vulnerabilitypassedpassedpassedpassed
31fix-gitfailedpassedpassedpassedverification_failed
32fix-ocaml-gcpassedpassedpassedpassed
33gcode-to-textfailedfailedfailedfailedbudget_exhaustedbudget_exhaustedbudget_exhaustedbudget_exhausted
34git-leak-recoverypassedpassedpassedpassed
35git-multibranchpassedpassedpassedpassed
36gpt2-codegolffailedfailedfailedfailedbudget_exhaustedbudget_exhaustedbudget_exhaustedbudget_exhausted
37headless-terminalpassedpassedpassedpassed
38hf-model-inferencepassedpassedpassedpassed
39install-windows-3.11passedpassedpassedfailedverification_failed
40kv-store-grpcpassedfailedpassedfailedverification_failedverification_failed
41large-scale-text-editingpassedpassedpassedpassed
42largest-eigenvalfailedpassedfailedpassedbudget_exhaustedbudget_exhausted
43llm-inference-batching-schedulerpassedpassedpassedpassed
44log-summary-date-rangespassedpassedpassedpassed
45mailmanpassedpassedpassedpassed
46make-doom-for-mipsfailedfailedfailedfailedbudget_exhaustedbudget_exhaustedbudget_exhaustedbudget_exhausted
47make-mips-interpreterfailedpassedfailedfailedverification_failedbudget_exhaustedbudget_exhausted
48mcmc-sampling-stanpassedpassedpassedfailedverification_failed
49merge-diff-arc-agi-taskpassedpassedpassedpassed
50model-extraction-relu-logitspassedpassedfailedpassedbudget_exhausted
51modernize-scientific-stackpassedpassedpassedpassed
52mteb-leaderboardfailedpassedpassedpassedverification_failed
53mteb-retrievepassedpassedpassedfailedverification_failed
54multi-source-data-mergerpassedpassedpassedpassed
55nginx-request-loggingpassedpassedpassedpassed
56openssl-selfsigned-certpassedpassedpassedpassed
57overfull-hboxpassedpassedpassedfailedbudget_exhausted
58password-recoverypassedpassedfailedpassedbudget_exhausted
59path-tracingpassedpassedfailedpassedbudget_exhausted
60path-tracing-reversefailedfailedfailedfailedbudget_exhaustedbudget_exhaustedbudget_exhaustedbudget_exhausted
61polyglot-c-pypassedpassedpassedfailedverification_failed
62polyglot-rust-cpassedpassedpassedpassed
63portfolio-optimizationpassedpassedpassedpassed
64protein-assemblypassedfailedfailedpassedverification_failedbudget_exhausted
65prove-plus-commpassedpassedpassedpassed
66pypi-serverpassedpassedpassedfailedverification_failed
67pytorch-model-clifailedfailedfailedpassedverification_failedverification_failedverification_failed
68pytorch-model-recoveryfailedpassedpassedunscoredverification_failedplumbing_failed
69qemu-alpine-sshpassedfailedpassedfailedverification_failedbudget_exhausted
70qemu-startuppassedpassedpassedfailedverification_failed
71query-optimizepassedpassedpassedfailedverification_failed
72raman-fittingfailedfailedfailedfailedbudget_exhaustedbudget_exhaustedbudget_exhaustedbudget_exhausted
73regex-chesspassedfailedfailedunscoredverification_failedbudget_exhaustedinfra_failed
74regex-logpassedpassedpassedpassed
75reshard-c4-datapassedpassedpassedpassed
76rstan-to-pystanpassedpassedpassedpassed
77sam-cell-segpassedpassedfailedpassedverification_failed
78sanitize-git-repopassedfailedpassedpassedverification_failed
79schemelike-metacircular-evalpassedpassedfailedfailedbudget_exhaustedverification_failed
80sparql-universitypassedpassedpassedpassed
81sqlite-db-truncatepassedpassedpassedpassed
82sqlite-with-gcovpassedpassedpassedpassed
83torch-pipeline-parallelismfailedpassedfailedfailedbudget_exhaustedverification_failedbudget_exhausted
84torch-tensor-parallelismfailedfailedfailedfailedverification_failedbudget_exhaustedverification_failedverification_failed
85train-fasttextfailedfailedfailedfailedbudget_exhaustedbudget_exhaustedbudget_exhaustedbudget_exhausted
86tune-mjcfpassedpassedfailedpassedbudget_exhausted
87video-processingfailedfailedfailedfailedverification_failedverification_failedverification_failedverification_failed
88vulnerable-secretpassedpassedpassedpassed
89winning-avg-corewarspassedpassedfailedpassedbudget_exhausted
90write-compressorfailedpassedfailedfailedbudget_exhaustedbudget_exhaustedverification_failed