Historical multi-task benchmark · Provisional

Phase 2: Refactoring

One of five Phase 2 task rankings. This table faithfully reproduces the 31 recorded results for refactoring, including public and hidden pass status, four-dimensional expert review, measured solution time, and execution-record status fields.

This is provisional historical evidence, not part of the current isolated ranking. See the retry-policy patch results or the benchmark index.

Historical / Provisional — not a blind benchmark
31candidates / records
146public passes, all tasks
134hidden passes, all tasks
0forbidden changes

Complete candidate results

Activate any column heading to sort. Activate it again to reverse direction.

31 rows

All 31 Phase 2 refactoring candidate records.
1 opencode-go/grok-4.509-grok-4-5 pass pass 10 10 9 10 9.75 32.583 completed 0 0 record ↗
2 opencode-go/hy314-hy3 pass pass 10 10 9 10 9.75 33.916 completed 0 0 record ↗
3 opencode/claude-sonnet-552-claude-sonnet-5 pass pass 10 10 9 10 9.75 36.677 completed 0 0 record ↗
4 opencode-go/gpt-5.6-luna01-gpt-5-6-luna pass pass 10 10 9 10 9.75 37.242 completed 0 0 record ↗
5 opencode/claude-haiku-4-551-claude-haiku-4-5 pass pass 10 10 9 10 9.75 42.257 completed 0 0 record ↗
6 opencode/nemotron-3.5-lightning-free33-nemotron-3-5-lightning-free pass pass 10 10 9 10 9.75 44.881 completed 0 0 record ↗
7 opencode/deepseek-v4-flash-free22-deepseek-v4-flash-free pass pass 10 10 9 10 9.75 48.012 completed 0 0 record ↗
8 opencode-go/mimo-v2.513-mimo-v2-5 pass pass 10 10 9 10 9.75 52.618 completed 0 0 record ↗
9 opencode-go/kimi-k2.616-kimi-k2-6 pass pass 10 10 9 10 9.75 54.125 completed 0 0 record ↗
10 gpt-5.6-terra48-gpt-5-6-terra pass pass 10 10 9 10 9.75 54.839 completed 0 0 record ↗
11 opencode-go/glm-5.115-glm-5-1 pass pass 10 10 9 10 9.75 55.172 completed 0 0 record ↗
12 opencode-go/minimax-m306-minimax-m3 pass pass 10 10 9 10 9.75 67.402 completed 0 0 record ↗
13 opencode-go/mimo-v2.5-pro07-mimo-v2-5-pro pass pass 10 10 9 10 9.75 68.297 completed 0 0 record ↗
14 opencode/nemotron-3-ultra-free35-nemotron-3-ultra-free pass pass 10 10 9 10 9.75 73.568 completed 0 0 record ↗
15 gpt-5.6-luna46-gpt-5-6-luna pass pass 10 10 9 10 9.75 82.673 completed 0 0 record ↗
16 gpt-5.6-sol47-gpt-5-6-sol pass pass 10 10 9 10 9.75 82.939 completed 0 0 record ↗
17 gpt-5.449-gpt-5-4 pass pass 10 10 9 10 9.75 95.703 completed 0 0 record ↗
18 opencode-go/glm-5.205-glm-5-2 pass pass 10 10 9 10 9.75 102.022 completed 0 0 record ↗
19 opencode-go/kimi-k2.7-code03-kimi-k2-7-code pass pass 10 10 9 10 9.75 102.408 completed 0 0 record ↗
20 opencode/hy3-free27-hy3-free pass pass 10 10 9 10 9.75 105.647 completed 0 0 record ↗
21 opencode/big-pickle19-big-pickle pass pass 10 10 9 10 9.75 114.751 completed 0 0 record ↗
22 opencode-go/deepseek-v4-pro04-deepseek-v4-pro pass pass 10 10 9 10 9.75 137.686 completed 0 0 record ↗
23 opencode/laguna-s-2.1-free20-laguna-s-2-1-free pass pass 10 10 9 10 9.75 439.532 completed 0 0 record ↗
24 opencode/claude-opus-553-claude-opus-5 pass pass 10 10 8 10 9.50 53.478 completed 0 0 record ↗
25 opencode-go/minimax-m2.717-minimax-m2-7 pass pass 10 10 8 10 9.50 61.998 completed 0 0 record ↗
26 gpt-5.3-codex-spark18-gpt-5-3-codex-spark pass pass 10 10 8 10 9.50 77.442 completed 0 0 record ↗
27 gpt-5.4-mini50-gpt-5-4-mini pass pass 10 10 8 10 9.50 109.280 completed 0 0 record ↗
28 opencode-go/deepseek-v4-flash11-deepseek-v4-flash pass pass 10 10 8 10 9.50 123.550 completed 0 0 record ↗
29 opencode-go/kimi-k310-kimi-k3 pass pass 10 10 8 10 9.50 146.596 completed 0 0 record ↗
N/A opencode/mimo-v2.5-free28-mimo-v2-5-free fail fail N/A N/A N/A N/A N/A 75.239 completed 0 1 record ↗
N/A opencode-go/qwen3.7-plus02-qwen3-7-plus fail fail N/A N/A N/A N/A N/A 900.003 completed — 1 record ↗

Source data and evidence

Generated from the Phase 2 records and expert reviews at commit f6e0d4ed4df2690f66b66d656012238d9cfe5add. Times are agent wall-clock solution durations. Public and hidden results remain separate objective evidence; expert scores use four 0–10 criteria and Overall is their arithmetic mean. No-patch outcomes remain N/A and do not count as code-quality failures.