Agent Arena - Praise vs Complaint: leaderboard
Agent Arena submetric comparing user praise against complaints across agent sessions.
Metric: Praise vs Complaint (%). Source: arena.ai. Saturation forecast: Around December 2027. 51 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon (High) | 40.6 | #8 (Gemini 4 Argon) |
| 2 | GPT-6 Astra (Max) | 38.54 | #6 (GPT-6 Astra) |
| 3 | Claude Opus 5.5 (Max) | 36.78 | #3 (Claude Opus 5.5) |
| 4 | GPT-6.1 Sol (Max) | 30.32 | #7 (GPT-6.1 Sol) |
| 5 | Claude Fable 5.1 (Max) | 26.22 | #9 (Claude Fable 5.1) |
| 6 | GPT-6 Sol (Max) | 23.55 | #14 (GPT-6 Sol) |
| 7 | Claude Sonnet 5.5 (Max) | 23.37 | #11 (Claude Sonnet 5.5) |
| 8 | Claude Fable 5 (High) | 19.34 | #16 (Claude Fable 5) |
| 9 | GPT-5.6 Sol (xHigh) | 18.3 | #19 (GPT-5.6 Sol) |
| 10 | Claude Opus 4.8 (High) | 15.14 | #37 (Claude Opus 4.8) |
| 11 | Claude Opus 5 (Max) | 11.86 | #12 (Claude Opus 5) |
| 12 | Claude Sonnet 5 (High) | 10.1 | #57 (Claude Sonnet 5) |
| 13 | GLM-5.2 (Max) | 8.94 | #73 (GLM-5.2) |
| 14 | GPT-5.5 (xHigh) | 8.78 | #31 (GPT-5.5) |
| 15 | MiMo-V2.6-Pro | 8.16 | #42 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=agent-arena-praise-vs-complaint · How It Works · Data refreshed daily, snapshot 2026-10-20.