Live Dashboard of PRs collections and SWE Tasks Generation
Live state of GitHub PR collection and verifiable SWE-Bench task generation across 8 languages. Detailed per-language analysis is collapsed below — click any section to expand.
Language Progress
| Language | PRs collected | Last 1h | Last 24h | Valid SWE | Last 1h | Last 24h | Processed | Success rate |
|---|---|---|---|---|---|---|---|---|
| Cc | 32,357 | 0 | 0 | 9,715 | 0 | +4 | 32,357 | |
| C++cpp | 48,174 | 0 | +1 | 4,047 | 0 | +3 | 25,554 | |
| Gogo | 132,103 | 0 | 0 | 8,163 | +2 | +24 | 97,854 | |
| Javajava | 89,031 | 0 | 0 | 4,060 | +1 | +18 | 88,907 | |
| JavaScriptjs | 39,682 | 0 | 0 | 7,202 | +2 | +24 | 39,682 | |
| Pythonpy | 105,775 | 0 | +4 | 5,073 | +1 | +8 | 105,661 | |
| Rustrust | 71,902 | 0 | 0 | 5,525 | 0 | +9 | 71,859 | |
| TypeScriptts | 70,493 | 0 | +2 | 6,477 | 0 | +20 | 63,582 |
Run Parameters
| Language | Eval model (OPENAI) | Completion model (ANTHROPIC) | Concurrency | min_source_files | max_source_files |
|---|---|---|---|---|---|
| C | gpt-5.4 | claude-sonnet-4-6 | 12 | 2 | 15 |
| C++ | Qwen3.6-35B-A3B | Qwen3.6-35B-A3B | 8 | 2 | 15 |
| Go | Qwen3.6-35B-A3B | Qwen3.6-35B-A3B | 12 | 2 | 10 |
| Java | gpt-5.4 | claude-sonnet-4-6 | 8 | 2 | 10 |
| JavaScript | Qwen3.6-35B-A3B | Qwen3.6-35B-A3B | 12 | 2 | 10 |
| Python | glm-5 | claude-sonnet-4-6 | 12 | 3 | 15 |
| Rust | Qwen3.6-35B-A3B | Qwen3.6-35B-A3B | 8 | 2 | 10 |
| TypeScript | Qwen3.6-35B-A3B | Qwen3.6-35B-A3B | 12 | 2 | 10 |
Failure Reason Breakdown
click to expand
| Language | Processed | Valid SWE | Failed | trivial_pr | validation | infra_error | timeout | workflow_error | Other |
|---|---|---|---|---|---|---|---|---|---|
| C | 32,357 | 9,715 | 22,642 | 16,043 | 2,858 | 3,747 | 2 | 277 | 1 |
| C++ | 25,554 | 4,047 | 21,507 | 4,866 | 2,679 | 15,275 | 159 | 509 | 266 |
| Go | 97,854 | 8,163 | 89,691 | 26,441 | 12,539 | 47,658 | 1,596 | 1,059 | 386 |
| Java | 88,907 | 4,060 | 84,847 | 23,481 | 7,987 | 43,028 | 1,224 | 7,932 | 1,601 |
| JavaScript | 39,682 | 7,202 | 32,480 | 16,895 | 2,847 | 13,432 | 421 | 267 | 0 |
| Python | 105,661 | 5,073 | 100,588 | 35,813 | 10,941 | 54,109 | 936 | 388 | 120 |
| Rust | 71,859 | 5,525 | 66,334 | 21,807 | 7,200 | 34,511 | 1,212 | 1,029 | 1,234 |
| TypeScript | 63,582 | 6,477 | 57,105 | 17,820 | 8,467 | 28,463 | 1,762 | 909 | 11 |
trivial_pr: the PR was judged by the LLM as too trivial (e.g. only config, docs, or dependency-version changes) and unsuitable as a SWE task.
validation: validation failed after task generation (the NOP agent did not return reward=0, or the ORACLE agent did not return reward=1).
infra_error: infrastructure error (Docker build failure, network timeout, insufficient disk space, etc.).
timeout: processing timed out (per-PR total timeout or Claude Code session timeout).
workflow_error: workflow error (PR metadata fetch failure, worktree creation failure, patch generation failure, etc.).
fix.patch Complexity
click to expand
| Language | Valid SWE Count | Avg fix.patch lines | Avg fix.patch hunks | Avg fix.patch files |
|---|---|---|---|---|
| C | 9,715 | 336.48 | 17.94 | 5.85 |
| C++ | 4,047 | 286.47 | 13.75 | 5.10 |
| Go | 8,163 | 212.10 | 12.61 | 4.34 |
| Java | 4,060 | 162.99 | 10.50 | 4.23 |
| JavaScript | 7,202 | 77.13 | 6.30 | 2.80 |
| Python | 5,073 | 152.25 | 11.04 | 3.85 |
| Rust | 5,525 | 225.54 | 13.17 | 4.10 |
| TypeScript | 6,477 | 157.70 | 9.60 | 4.13 |
Metric Definitions
click to expand
Difficulty score (difficulty_score)
Reads each valid task directory's solution/fix.patch, tests/, and instruction.md, scored statically with zero API calls by src/swegen/scoring.py.
The current formula uses log-scale continuous scoring to avoid mid-sized patches becoming hard too early. Weights: patch_scope 38%, logic_complexity 32%, context_breadth 15%, test_complexity 10%, instruction_complexity 5%.
Label thresholds: easy <= 4.0, medium <= 7.0, hard > 7.0.
Tag generation and display
tags are not computed live by the dashboard; they are generated by the LLM from PR information when swegen builds the task, and written to [metadata].tags in task.toml.
The prompt asks for tags in four parts: programming language, project layer/domain, framework/library or specific topic, and a domain-independent bug class (e.g. missing-fallback, incomplete-validation). The dashboard reads existing task.toml files, counts each language's tag occurrences and share, and treats the 4th tag as the bug class for the Bug-Class panels below.
fix.patch statistics
Patch stats come from each valid task's solution/fix.patch, filtering code files by language extension, consistent with the code-only stats in upload_march_swe_to_hf.py.
Avg fix.patch lines counts added/removed lines in code-file diffs; Avg fix.patch hunks counts @@ hunks; Avg fix.patch files counts the code files involved.
difficulty_label Distribution
click to expand
| Language | easy / medium / hard | easy | medium | hard |
|---|---|---|---|---|
| C | 869 / 6417 / 2421 | 869 | 6,417 | 2,421 |
| C++ | 431 / 2514 / 1097 | 431 | 2,514 | 1,097 |
| Go | 648 / 5897 / 1612 | 648 | 5,897 | 1,612 |
| Java | 451 / 2627 / 978 | 451 | 2,627 | 978 |
| JavaScript | 1090 / 5334 / 777 | 1,090 | 5,334 | 777 |
| Python | 273 / 3253 / 1523 | 273 | 3,253 | 1,523 |
| Rust | 384 / 3270 / 1869 | 384 | 3,270 | 1,869 |
| TypeScript | 584 / 4787 / 1106 | 584 | 4,787 | 1,106 |
difficulty_score Overview
click to expand
| Language | count | min | p25 | median | mean | p75 | max |
|---|---|---|---|---|---|---|---|
| C | 9,707 | 2.4 | 4.9 | 6.0 | 5.97 | 7.0 | 9.2 |
| C++ | 4,042 | 2.5 | 4.9 | 6.0 | 5.99 | 7.2 | 9.1 |
| Go | 8,157 | 2.6 | 4.9 | 5.8 | 5.86 | 6.8 | 9.1 |
| Java | 4,056 | 2.8 | 4.8 | 5.9 | 5.89 | 7.0 | 9.2 |
| JavaScript | 7,201 | 2.6 | 4.4 | 5.2 | 5.36 | 6.2 | 9.2 |
| Python | 5,049 | 2.6 | 5.2 | 6.2 | 6.22 | 7.3 | 9.1 |
| Rust | 5,523 | 2.7 | 5.2 | 6.3 | 6.26 | 7.4 | 9.0 |
| TypeScript | 6,477 | 2.7 | 4.7 | 5.6 | 5.72 | 6.6 | 9.2 |
Global Top Tags
click to expand
Per-Language Tag Distribution
click to expand
Global Top Bug Classes
click to expand
Bug class is the 4th tag in task.toml -> [metadata].tags: a domain-independent label describing the defect mechanism (e.g. missing-fallback, incomplete-validation, off-by-one-error). Generated by the LLM during swegen create and backfilled into legacy 3-tag tasks via swegen backfill-tags.
Per-Language Bug-Class Distribution
click to expand
Top bug classes per mainstream language. Counts are over tasks whose task.toml already carries a 4-tag entry; tasks still on the legacy 3-tag schema do not contribute until the backfill catches up.