LMArcade - terminus-2: leaderboard
LMArcade head-to-head human-voted playable-game Elo leaderboard inside the terminus-2 coding-agent harness (builds >= 5).
Metric: Elo Rating. Source: www.lmarcade.com. Saturation forecast: Around September 2027. 26 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5 | 1689 | #26 | |
| 2 | Claude Fable 5 | 1687 | #32 | |
| 3 | GPT-5.5 | Medium | 1686 | #56 |
| 4 | Claude Opus 4.7 | 1665 | #86 | |
| 5 | Claude Sonnet 4.6 | 1656 | #179 | |
| 6 | GPT-5.4 | Medium | 1605 | #138 |
| 7 | Claude Opus 4.8 | 1596 | #64 | |
| 8 | Kimi K3 | 1560 | #62 | |
| 9 | GLM-5.1 | 1542 | #200 | |
| 10 | Qwen 3.6 Max | 1511 | #192 | |
| 11 | Kimi K2.6 | 1497 | #197 | |
| 12 | MiniMax-M2.7 | 1495 | #539 | |
| 13 | Gemini 3.1 Pro (Preview) | 1491 | #102 | |
| 14 | MiMo-V2.5-Pro | 1467 | #292 | |
| 15 | MiniMax-M3 | 1460 | #290 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=lmarcade-terminus-2 · How It Works · Data refreshed daily, snapshot 2026-11-22.