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 | 0 | 32,357 | |
| C++cpp | 48,175 | 0 | +1 | 4,052 | 0 | +5 | 27,502 | |
| Gogo | 132,104 | 0 | +1 | 8,196 | +2 | +36 | 100,960 | |
| Javajava | 89,032 | +1 | +1 | 4,080 | 0 | +21 | 88,911 | |
| JavaScriptjs | 39,682 | 0 | 0 | 7,220 | +3 | +21 | 39,682 | |
| Pythonpy | 105,777 | 0 | +2 | 5,087 | +1 | +15 | 105,670 | |
| Rustrust | 71,903 | 0 | +1 | 5,540 | 0 | +16 | 71,862 | |
| TypeScriptts | 70,493 | 0 | 0 | 6,504 | +1 | +28 | 65,470 |
Run Parameters
| Language | Eval model (OPENAI) | Completion model (ANTHROPIC) | Concurrency | min_source_files | max_source_files |
|---|---|---|---|---|---|
| C | glm-5 | 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 | glm-5 | 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 | 17,581 | 4,316 | 929 | 2 | 98 | 2 |
| C++ | 27,502 | 4,052 | 23,450 | 5,755 | 3,631 | 15,363 | 159 | 525 | 266 |
| Go | 100,960 | 8,196 | 92,764 | 27,867 | 14,237 | 47,677 | 1,577 | 1,059 | 335 |
| Java | 88,911 | 4,080 | 84,831 | 23,960 | 8,462 | 42,256 | 1,190 | 7,769 | 1,601 |
| JavaScript | 39,682 | 7,220 | 32,462 | 16,984 | 3,327 | 12,892 | 380 | 261 | 0 |
| Python | 105,670 | 5,087 | 100,583 | 37,255 | 11,730 | 51,917 | 901 | 380 | 120 |
| Rust | 71,862 | 5,540 | 66,322 | 22,254 | 7,866 | 33,425 | 1,180 | 1,023 | 1,234 |
| TypeScript | 65,470 | 6,504 | 58,966 | 19,017 | 9,913 | 27,698 | 1,764 | 891 | 10 |
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++ | 4,052 | 286.29 | 13.75 | 5.09 |
| Go | 8,196 | 211.61 | 12.60 | 4.34 |
| Java | 4,080 | 162.86 | 10.51 | 4.22 |
| JavaScript | 7,220 | 77.09 | 6.30 | 2.80 |
| Python | 5,087 | 152.58 | 11.07 | 3.85 |
| Rust | 5,540 | 225.32 | 13.16 | 4.10 |
| TypeScript | 6,504 | 157.33 | 9.59 | 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++ | 432 / 2517 / 1098 | 432 | 2,517 | 1,098 |
| Go | 652 / 5920 / 1618 | 652 | 5,920 | 1,618 |
| Java | 452 / 2641 / 983 | 452 | 2,641 | 983 |
| JavaScript | 1093 / 5348 / 778 | 1,093 | 5,348 | 778 |
| Python | 273 / 3261 / 1529 | 273 | 3,261 | 1,529 |
| Rust | 386 / 3281 / 1871 | 386 | 3,281 | 1,871 |
| TypeScript | 588 / 4807 / 1109 | 588 | 4,807 | 1,109 |
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++ | 4,047 | 2.5 | 4.9 | 6.0 | 5.99 | 7.2 | 9.1 |
| Go | 8,190 | 2.6 | 4.9 | 5.8 | 5.86 | 6.8 | 9.1 |
| Java | 4,076 | 2.8 | 4.8 | 5.9 | 5.90 | 7.0 | 9.2 |
| JavaScript | 7,219 | 2.6 | 4.4 | 5.2 | 5.36 | 6.2 | 9.2 |
| Python | 5,063 | 2.6 | 5.2 | 6.2 | 6.22 | 7.3 | 9.1 |
| Rust | 5,538 | 2.7 | 5.2 | 6.3 | 6.26 | 7.4 | 9.0 |
| TypeScript | 6,504 | 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.