LMArena Agent Arena Praise vs Complaint
Agents · 2026-06-04
Signed percentage-point Agent Arena diagnostic signal comparing positive user feedback against complaints. Values may be negative when a model is below the leaderboard baseline; higher values indicate more favorable user reactions to the agent’s work.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 25.6 |
| Claude Fable 5 | 24.4 |
| GPT-5.6 Sol | 21.9 |
| Opus 4.8 | 21.0 |
| Kimi K3 | 17.5 |
| Sonnet 5 | 16.1 |
| GLM-5.2 | 13.8 |
| GPT-5.5 | 12.9 |
| Opus 4.7 | 12.3 |
| Opus 4.6 | 10.1 |
| Grok 4.5 | 5.7 |
| GPT-5.6 Luna | 4.8 |
| GPT-5.6 Terra | 4.5 |
| GPT-5.4 | 3.5 |
| Kimi K2.7 Code | 3.4 |
| Hy3 | 2.8 |
| Kimi K2.6 | 1.6 |
| Gemini 3.1 Pro Preview | 1.3 |
| Sonnet 4.6 | 0.9 |
| GLM-5.1 | 0.5 |
| Gemini 3.5 Flash | -3.6 |
| Gemma 4 31B IT | -3.9 |
| Muse Spark 1.1 | -4.6 |
| DeepSeek-V4-Pro | -5.4 |
| Qwen3.7-Max | -5.9 |
| Gemini 3.6 Flash | -6.2 |
| Qwen3.7-Plus | -8.0 |
| MiMo-V2.5-Pro | -8.1 |
| DeepSeek-V4-Flash | -8.4 |
| MiniMax M3 | -9.0 |
| Grok Build 0.1 | -10.6 |
| Gemini 3 Flash Preview | -11.8 |
| Nemotron 3 Ultra 550B A55B | -13.6 |
| Grok 4.3 | -14.2 |
| MiniMax M2.7 | -15.7 |
| Inkling | -15.8 |
| Gemini 3.5 Flash-Lite | -17.6 |