Historical five-task benchmark: aggregate results
An aggregate of five different coding tasks: repairing ledger logic, implementing feature flags, refactoring event processing, navigating a repository to fix status labels, and strengthening range parsing and edge-case tests. Each model has one record per task; the aggregate combines objective results and four-dimensional expert reviews across all five.
This is provisional historical evidence, not part of the current isolated ranking. See the retry-policy patch results or the benchmark index.
Complete candidate results
Activate any column heading to sort. Activate it again to reverse direction.
31 rows
| 1 | opencode-go/deepseek-v4-pro04-deepseek-v4-pro | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 9.0 | 10.0 | 9.75 | 65.574 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 2 | opencode-go/glm-5.205-glm-5-2 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 9.0 | 10.0 | 9.75 | 119.742 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 3 | opencode-go/gpt-5.6-luna01-gpt-5-6-luna | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 38.673 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 4 | opencode/deepseek-v4-flash-free22-deepseek-v4-flash-free | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 51.981 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 5 | opencode/claude-sonnet-552-claude-sonnet-5 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 68.213 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 6 | opencode-go/deepseek-v4-flash11-deepseek-v4-flash | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 74.143 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 7 | gpt-5.6-terra48-gpt-5-6-terra | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 87.055 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 8 | opencode-go/kimi-k2.616-kimi-k2-6 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 91.592 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 9 | opencode-go/kimi-k2.7-code03-kimi-k2-7-code | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 99.379 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 10 | opencode-go/minimax-m306-minimax-m3 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 101.459 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 11 | gpt-5.449-gpt-5-4 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 119.703 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 12 | opencode-go/glm-5.115-glm-5-1 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.8 | 10.0 | 9.70 | 135.099 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 13 | opencode-go/grok-4.509-grok-4-5 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.6 | 10.0 | 9.65 | 29.899 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 14 | opencode-go/mimo-v2.5-pro07-mimo-v2-5-pro | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.6 | 10.0 | 9.65 | 105.134 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 15 | gpt-5.6-sol47-gpt-5-6-sol | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.6 | 10.0 | 9.65 | 121.107 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 16 | gpt-5.4-mini50-gpt-5-4-mini | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.6 | 10.0 | 9.65 | 124.081 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 17 | gpt-5.6-luna46-gpt-5-6-luna | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.6 | 10.0 | 9.65 | 195.330 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 18 | opencode-go/kimi-k310-kimi-k3 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.4 | 10.0 | 9.60 | 189.396 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 19 | gpt-5.3-codex-spark18-gpt-5-3-codex-spark | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.2 | 10.0 | 9.55 | 60.725 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 20 | opencode/claude-opus-553-claude-opus-5 | 5/5 | 5/5 | 5 | 5 | 10.0 | 10.0 | 8.2 | 10.0 | 9.55 | 143.420 | 5/5 completed | 5/5 | 5/5 | records ↗ |
| 21 | opencode-go/mimo-v2.513-mimo-v2-5 | 5/5 | 4/5 | 5 | 4 | 9.4 | 9.0 | 8.8 | 10.0 | 9.30 | 72.584 | 5/5 completed | 5/5 | 4/5 | records ↗ |
| 22 | opencode/hy3-free27-hy3-free | 5/5 | 4/5 | 5 | 4 | 9.4 | 9.0 | 8.6 | 10.0 | 9.25 | 59.818 | 5/5 completed | 5/5 | 4/5 | records ↗ |
| 23 | opencode/big-pickle19-big-pickle | 5/5 | 4/5 | 5 | 4 | 9.0 | 8.6 | 9.0 | 10.0 | 9.15 | 68.279 | 5/5 completed | 5/5 | 4/5 | records ↗ |
| 24 | opencode-go/hy314-hy3 | 5/5 | 4/5 | 5 | 4 | 9.0 | 8.6 | 8.8 | 10.0 | 9.10 | 42.575 | 5/5 completed | 5/5 | 4/5 | records ↗ |
| 25 | opencode/claude-haiku-4-551-claude-haiku-4-5 | 5/5 | 4/5 | 5 | 4 | 9.0 | 8.6 | 8.2 | 10.0 | 8.95 | 55.642 | 5/5 completed | 5/5 | 4/5 | records ↗ |
| 26 | opencode-go/minimax-m2.717-minimax-m2-7 | 5/5 | 3/5 | 5 | 3 | 8.6 | 7.8 | 8.8 | 10.0 | 8.80 | 88.774 | 5/5 completed | 5/5 | 3/5 | records ↗ |
| 27 | opencode/nemotron-3.5-lightning-free33-nemotron-3-5-lightning-free | 5/5 | 3/5 | 5 | 3 | 8.4 | 7.6 | 9.0 | 10.0 | 8.75 | 55.641 | 5/5 completed | 5/5 | 3/5 | records ↗ |
| N/A | opencode/nemotron-3-ultra-free35-nemotron-3-ultra-free | 4/5 | 3/5 | 4 | 3 | 8.8 | 8.3 | 9.0 | 10.0 | 9.00 | 81.606 | 5/5 completed | 4/5 | 3/5 | records ↗ |
| N/A | opencode/mimo-v2.5-free28-mimo-v2-5-free | 4/5 | 2/5 | 4 | 2 | 8.0 | 7.0 | 8.8 | 10.0 | 8.44 | 168.850 | 5/5 completed | 5/5 | 2/5 | records ↗ |
| N/A | opencode/laguna-s-2.1-free20-laguna-s-2-1-free | 3/5 | 3/5 | 3 | 3 | 10.0 | 10.0 | 8.7 | 10.0 | 9.67 | 499.955 | 5/5 completed | 3/5 | 3/5 | records ↗ |
| N/A | opencode-go/qwen3.7-plus02-qwen3-7-plus | 0/5 | 0/5 | 0 | 0 | N/A | N/A | N/A | N/A | N/A | 900.024 | 5/5 completed | 0/5 | 0/5 | records ↗ |
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.