LMArcade - mini-swe-agent: leaderboard
LMArcade head-to-head human-voted playable-game Elo leaderboard inside the mini-swe-agent coding-agent harness (builds >= 5).
Metric: Elo Rating. Source: www.lmarcade.com. Saturation forecast: Around September 2027. 25 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Fable 5 | 1676 | #32 | |
| 2 | Claude Opus 4.7 | 1673 | #86 | |
| 3 | Claude Opus 5 | 1669 | #26 | |
| 4 | GPT-5.5 | Medium | 1660 | #56 |
| 5 | Claude Opus 4.8 | 1658 | #64 | |
| 6 | Claude Sonnet 4.6 | 1643 | #179 | |
| 7 | Claude Sonnet 5 | 1622 | #124 | |
| 8 | Kimi K3 | 1573 | #62 | |
| 9 | DeepSeek V4 Pro | 1570 | #201 | |
| 10 | DeepSeek V4 Flash | 1527 | #273 | |
| 11 | Qwen 3.5 397B A17B | 1516 | #270 | |
| 12 | Kimi K2.6 | 1513 | #197 | |
| 13 | GLM-5.1 | 1513 | #200 | |
| 14 | GPT-5.4 | Medium | 1503 | #138 |
| 15 | Gemma 4 31B | 1483 | #390 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=lmarcade-mini-swe-agent · How It Works · Data refreshed daily, snapshot 2026-11-22.