Files
1jehuang--jcode/scripts/tb_baseline_cc_opus48.tsv
wehub-resource-sync a789495a98
CI / Quality Guardrails (push) Waiting to run
CI / Build & Test (macos-latest) (push) Waiting to run
CI / Build & Test (ubuntu-latest) (push) Waiting to run
CI / Build & Test (windows-latest) (push) Waiting to run
CI / Format (push) Waiting to run
CI / PowerShell Syntax (push) Waiting to run
CI / Windows Cross-Target Check (Linux) (push) Waiting to run
FreeBSD Smoke / FreeBSD Smoke (x86_64) (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:10:34 +08:00

2.6 KiB

1# Claude Code + Opus 4.8 baseline on Terminal-Bench (5 trials/task). jcode must never do worse.
2# tasktrialsresolvedrate
3adaptive-rejection-sampler5480.0
4bn-fit-modify55100.0
5break-filter-js-from-html55100.0
6build-cython-ext55100.0
7build-pmars55100.0
8build-pov-ray55100.0
9caffe-cifar-1055100.0
10cancel-async-tasks5120.0
11chess-best-move5240.0
12circuit-fibsqrt55100.0
13cobol-modernization55100.0
14code-from-image55100.0
15compile-compcert5360.0
16configure-git-webserver5120.0
17constraints-scheduling55100.0
18count-dataset-tokens55100.0
19crack-7z-hash55100.0
20custom-memory-heap-crash55100.0
21db-wal-recovery500.0
22distribution-search55100.0
23dna-assembly5360.0
24dna-insert500.0
25extract-elf5360.0
26extract-moves-from-video500.0
27feal-differential-cryptanalysis55100.0
28feal-linear-cryptanalysis55100.0
29filter-js-from-html5360.0
30financial-document-processor5240.0
31fix-code-vulnerability55100.0
32fix-git55100.0
33fix-ocaml-gc55100.0
34gcode-to-text55100.0
35git-leak-recovery55100.0
36git-multibranch55100.0
37gpt2-codegolf5480.0
38headless-terminal55100.0
39hf-model-inference55100.0
40install-windows-3.115480.0
41kv-store-grpc55100.0
42large-scale-text-editing55100.0
43largest-eigenval5480.0
44llm-inference-batching-scheduler55100.0
45log-summary-date-ranges55100.0
46mailman55100.0
47make-doom-for-mips500.0
48make-mips-interpreter5480.0
49mcmc-sampling-stan55100.0
50merge-diff-arc-agi-task55100.0
51model-extraction-relu-logits500.0
52modernize-scientific-stack55100.0
53mteb-leaderboard55100.0
54mteb-retrieve5240.0
55multi-source-data-merger55100.0
56nginx-request-logging55100.0
57openssl-selfsigned-cert5480.0
58overfull-hbox5480.0
59password-recovery55100.0
60path-tracing5480.0
61path-tracing-reverse5480.0
62polyglot-c-py55100.0
63polyglot-rust-c55100.0
64portfolio-optimization5480.0
65protein-assembly500.0
66prove-plus-comm55100.0
67pypi-server55100.0
68pytorch-model-cli5240.0
69pytorch-model-recovery5360.0
70qemu-alpine-ssh5480.0
71qemu-startup55100.0
72query-optimize55100.0
73raman-fitting500.0
74regex-chess55100.0
75regex-log55100.0
76reshard-c4-data55100.0
77rstan-to-pystan5120.0
78sam-cell-seg5480.0
79sanitize-git-repo5480.0
80schemelike-metacircular-eval55100.0
81sparql-university55100.0
82sqlite-db-truncate55100.0
83sqlite-with-gcov55100.0
84torch-pipeline-parallelism5480.0
85torch-tensor-parallelism55100.0
86train-fasttext500.0
87tune-mjcf55100.0
88video-processing500.0
89vulnerable-secret55100.0
90winning-avg-corewars55100.0
91write-compressor5480.0