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
7beam-1-0-501b-a23b81.6
8claude-opus-4-681.42
9claude-opus-4-580.9
10deepseek-v4-pro-max80.6
11gemini-3-1-pro80.6
12minimax-m380.5
13qwen3-7-max80.4
14qwen3-7-max80.4
15kimi-k2-680.2
16minimax-m2-580.2
17kimi-k2-090580.2
18gpt-5-280
19claude-sonnet-4-679.6
20claude-sonnet-4-679.6
21deepseek-v4-flash-max79
22ornith-1-5-35b-a3b79
23mimo-v2-5-pro78.9
24qwen3-6-plus78.8
25dots3-note-preview78.4

SWE-bench Verified — Leaderboard

1 phaseActive

SWE-bench Verified Leaderboard

No self-reported entries.