SWE-gen 进度看板

收集 PR 总数

423,773

1h +41 / 24h +1,452

有效 SWE 总数

28,616

1h +3 / 24h +751

整体处理成功率

6.8%

Valid SWE / Collected PRs

difficulty_score 均值

5.76

median 5.7，count 28,571

语言进度

语言	收集 PR	过去 1h	过去 24h	有效 SWE	过去 1h	过去 24h	处理成功率
Cc	28,202	0	+77	7,734	0	+335	27.4%
C++cpp	43,066	0	+160	1,861	0	+28	4.3%
Gogo	87,517	0	0	4,415	0	+87	5.0%
Javajava	59,887	+4	+40	2,604	0	+25	4.3%
JavaScriptjs	30,786	0	+61	3,666	0	+7	11.9%
Pythonpy	68,032	0	+258	2,518	0	0	3.7%
Rustrust	50,420	+34	+34	2,470	0	+35	4.9%
TypeScriptts	55,863	+3	+822	3,348	+3	+234	6.0%

fix.patch 复杂度

语言	Valid SWE Count	Avg fix.patch lines	Avg fix.patch hunks	Avg fix.patch files
C	7,734	281.22	15.40	4.93
C++	1,861	334.96	11.37	4.51
Go	4,415	271.58	14.95	4.96
Java	2,604	169.54	10.83	4.41
JavaScript	3,666	73.31	6.22	2.76
Python	2,518	135.78	9.99	3.44
Rust	2,470	254.61	12.67	4.02
TypeScript	3,348	160.41	9.09	4.09

统计方法说明

难度打分 difficulty_score

读取每个有效任务目录的 solution/fix.patch、tests/ 和 instruction.md，由 src/swegen/scoring.py 使用零 API 静态评分。

当前公式采用 log-scale 连续评分，避免中等规模 patch 过早变成 hard。权重为：patch_scope 38%、logic_complexity 32%、context_breadth 15%、test_complexity 10%、instruction_complexity 5%。

label 阈值：easy <= 4.0，medium <= 7.0，hard > 7.0。

Tags 生成与展示

tags 不是看板现场计算的，而是在 swegen 构建任务时由 LLM 根据 PR 信息生成，并写入 task.toml 的 [metadata].tags。

prompt 要求 tags 按三段式生成：编程语言、项目层级/领域、框架/库名或具体主题。看板只读取已有 task.toml 并统计每个语言的 tag 出现次数和占比。

fix.patch 统计

patch 统计来自每个有效任务的 solution/fix.patch，并按语言扩展名过滤代码文件，口径与 upload_march_swe_to_hf.py 的 code-only 统计保持一致。

Avg fix.patch lines 统计代码文件 diff 中新增/删除行数；Avg fix.patch hunks 统计 @@ hunk 数；Avg fix.patch files 统计涉及的代码文件数。

difficulty_label 分布

语言	easy / medium / hard	easy	medium	hard
C	735 / 5189 / 1802	735	5,189	1,802
C++	320 / 1163 / 374	320	1,163	374
Go	369 / 3254 / 786	369	3,254	786
Java	346 / 1660 / 595	346	1,660	595
JavaScript	593 / 2724 / 348	593	2,724	348
Python	211 / 1725 / 561	211	1,725	561
Rust	260 / 1444 / 764	260	1,444	764
TypeScript	343 / 2536 / 469	343	2,536	469

difficulty_score 概览

语言	count	min	p25	median	mean	p75	max
C	7,726	2.4	4.9	5.9	5.91	7.0	9.2
C++	1,857	2.5	4.4	5.6	5.61	6.8	9.0
Go	4,409	2.6	4.9	5.8	5.81	6.7	9.1
Java	2,601	2.8	4.7	5.8	5.80	6.9	9.2
JavaScript	3,665	2.6	4.4	5.2	5.28	6.1	9.2
Python	2,497	2.6	4.9	5.8	5.90	6.9	8.9
Rust	2,468	2.7	4.9	6.2	6.10	7.4	9.0
TypeScript	3,348	2.7	4.6	5.5	5.58	6.5	8.9

全局 Top Tags

library12,948 (45.3%)

backend8,795 (30.8%)

cli3,994 (14.0%)

frontend1,677 (5.9%)

testing1,195 (4.2%)

react899 (3.1%)

http888 (3.1%)

framework770 (2.7%)

embedded567 (2.0%)

cpp396 (1.4%)

networking359 (1.3%)

async323 (1.1%)

kubernetes255 (0.9%)

graphql229 (0.8%)

postgresql226 (0.8%)

eslint217 (0.8%)

parsing204 (0.7%)

aws182 (0.6%)

kernel173 (0.6%)

compiler171 (0.6%)

angular171 (0.6%)

firmware170 (0.6%)

quic166 (0.6%)

git165 (0.6%)

json162 (0.6%)

redis149 (0.5%)

aem147 (0.5%)

security142 (0.5%)

rust141 (0.5%)

tls138 (0.5%)

每语言 Tags 分布

C c

library4,080 (52.8%)

backend1,884 (24.4%)

cli938 (12.1%)

embedded562 (7.3%)

cpp395 (5.1%)

networking287 (3.7%)

testing213 (2.8%)

postgresql186 (2.4%)

kernel173 (2.2%)

framework172 (2.2%)

firmware170 (2.2%)

quic161 (2.1%)

http146 (1.9%)

rust131 (1.7%)

bluetooth121 (1.6%)

tls119 (1.5%)

ruby113 (1.5%)

scheduler110 (1.4%)

cryptography102 (1.3%)

python88 (1.1%)

C++ cpp

library1,374 (74.0%)

backend295 (15.9%)

testing227 (12.2%)

cli151 (8.1%)

boost92 (5.0%)

framework74 (4.0%)

http68 (3.7%)

async62 (3.3%)

compiler41 (2.2%)

parsing38 (2.0%)

serialization36 (1.9%)

templates29 (1.6%)

actor-framework28 (1.5%)

arrayfire28 (1.5%)

formatting27 (1.5%)

logging21 (1.1%)

audio20 (1.1%)

sparql20 (1.1%)

iceberg19 (1.0%)

ranges19 (1.0%)

Go go

backend2,349 (53.3%)

cli1,178 (26.7%)

library986 (22.4%)

http332 (7.5%)

kubernetes223 (5.1%)

testing122 (2.8%)

docker98 (2.2%)

aws80 (1.8%)

framework71 (1.6%)

grpc68 (1.5%)

aws-sdk56 (1.3%)

git45 (1.0%)

dns45 (1.0%)

database44 (1.0%)

aws-lambda38 (0.9%)

security37 (0.8%)

terraform36 (0.8%)

blockchain36 (0.8%)

prometheus34 (0.8%)

templ34 (0.8%)

Java java

backend1,296 (49.8%)

library1,167 (44.9%)

aem147 (5.7%)

testing132 (5.1%)

spring104 (4.0%)

framework76 (2.9%)

http74 (2.8%)

android72 (2.8%)

json63 (2.4%)

sling57 (2.2%)

flink47 (1.8%)

cli40 (1.5%)

concurrency40 (1.5%)

grpc37 (1.4%)

nacos34 (1.3%)

mybatis33 (1.3%)

maven29 (1.1%)

parsing27 (1.0%)

sql-parser27 (1.0%)

websocket27 (1.0%)

JavaScript js

library1,797 (49.0%)

backend762 (20.8%)

frontend486 (13.3%)

cli435 (11.9%)

testing204 (5.6%)

react180 (4.9%)

eslint178 (4.9%)

framework176 (4.8%)

fastify118 (3.2%)

http105 (2.9%)

mongoose97 (2.6%)

webpack71 (1.9%)

typescript69 (1.9%)

express67 (1.8%)

svelte61 (1.7%)

lighthouse61 (1.7%)

aframe53 (1.4%)

async50 (1.4%)

apostrophecms48 (1.3%)

nodejs47 (1.3%)

Python py

backend1,096 (43.9%)

library915 (36.6%)

cli418 (16.7%)

ansible98 (3.9%)

fastapi78 (3.1%)

testing77 (3.1%)

framework66 (2.6%)

aiohttp62 (2.5%)

aws56 (2.2%)

django54 (2.2%)

http52 (2.1%)

click46 (1.8%)

dbt41 (1.6%)

black40 (1.6%)

async39 (1.6%)

openai39 (1.6%)

jinja235 (1.4%)

pipx34 (1.4%)

pytorch31 (1.2%)

litellm31 (1.2%)

Rust rust

library1,399 (56.7%)

cli576 (23.3%)

backend435 (17.6%)

testing162 (6.6%)

git88 (3.6%)

http86 (3.5%)

async75 (3.0%)

compiler58 (2.4%)

parsing55 (2.2%)

graphql55 (2.2%)

datafusion49 (2.0%)

substrate47 (1.9%)

macros45 (1.8%)

sql44 (1.8%)

actix-web44 (1.8%)

framework41 (1.7%)

parquet39 (1.6%)

blockchain31 (1.3%)

sqlparser28 (1.1%)

clap28 (1.1%)

TypeScript ts

library1,230 (36.7%)

frontend1,055 (31.5%)

react715 (21.4%)

backend678 (20.3%)

cli258 (7.7%)

angular170 (5.1%)

graphql133 (4.0%)

framework94 (2.8%)

electron94 (2.8%)

fullstack86 (2.6%)

github-actions59 (1.8%)

testing58 (1.7%)

vue55 (1.6%)

express48 (1.4%)

javascript45 (1.3%)

nextjs42 (1.3%)

eslint39 (1.2%)

xstate37 (1.1%)

zod36 (1.1%)

react-native36 (1.1%)