LMArcade - swe-agent: leaderboard
LMArcade head-to-head human-voted playable-game Elo leaderboard inside the swe-agent coding-agent harness (builds >= 5).
Metric: Elo Rating. Source: www.lmarcade.com. Saturation forecast: Around September 2027. 24 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Fable 5 | 1720 | #32 | |
| 2 | Claude Opus 5 | 1675 | #26 | |
| 3 | Claude Opus 4.8 | 1639 | #64 | |
| 4 | GPT-5.5 | Medium | 1607 | #56 |
| 5 | Claude Sonnet 5 | 1600 | #124 | |
| 6 | Claude Opus 4.7 | 1596 | #86 | |
| 7 | GPT-5.4 | Medium | 1582 | #138 |
| 8 | Claude Sonnet 4.6 | 1563 | #179 | |
| 9 | MiMo-V2.5-Pro | 1554 | #292 | |
| 10 | Gemini 3.1 Pro (Preview) | 1546 | #102 | |
| 11 | Gemini 3 Flash | 1531 | #180 | |
| 12 | Kimi K3 | 1526 | #62 | |
| 13 | Qwen 3.6 Max | 1525 | #192 | |
| 14 | DeepSeek V4 Pro | 1475 | #201 | |
| 15 | GLM-5.1 | 1472 | #200 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=lmarcade-swe-agent · How It Works · Data refreshed daily, snapshot 2026-11-22.