Benchgen

SWE-bench Verified — Results

RankModelScore
1claude-fable-595
2claude-mythos-preview93.9
3claude-opus-4-888.6
4claude-opus-4-787.6
5ornith-1-5-397b86
6claude-sonnet-585.2
7claude-opus-4-681.42
8claude-opus-4-580.9
9deepseek-v4-pro-max80.6
10gemini-3-1-pro80.6
11minimax-m380.5
12qwen3-7-max80.4
13qwen3-7-max80.4
14kimi-k2-680.2
15minimax-m2-580.2
16kimi-k2-090580.2
17gpt-5-280
18claude-sonnet-4-679.6
19claude-sonnet-4-679.6
20deepseek-v4-flash-max79
21ornith-1-5-35b-a3b79
22mimo-v2-5-pro78.9
23qwen3-6-plus78.8
24dots3-note-preview78.4
25gemini-3-flash78

SWE-bench Verified — Leaderboard

1 phaseActive

SWE-bench Verified Leaderboard

No self-reported entries.