EnterpriseArena — leaderboard
Metric: Full Survival % (self-reported). Source: benchmarklist.com. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 60 |
| 2 | Llama 3.1 8B Instruct | 40 |
| 3 | Grok 4.3 | 40 |
| 4 | Gemini 3.1 Pro (Preview) | 20 |
| 5 | Claude Opus 4.7 | 20 |
| 6 | Llama 3 8B Instruct | 20 |
| 7 | Qwen 3.5 9B | 20 |
| 8 | GLM-5 | 20 |
| 9 | Qwen 3.5 397B A17B | 20 |
| 10 | MiniMax-M2.7 | 20 |
| 11 | Llama 3.3 70B Instruct | 0 |
| 12 | GPT-5.4 | 0 |
| 13 | DeepSeek V3.1 | 0 |
| 14 | Gemma 4 31B | 0 |
| 15 | GLM-5.1 | 0 |
Interactive version: theaggregate.ai/benchmark?slug=enterprisearena · How the rankings work · Data refreshed daily, snapshot 2026-07-22.