Thrive Helpdesk - Difficult Tickets: leaderboard
Thrive Helpdesk - Difficult Tickets — 57native model/effort configurations, each52difficult helpdesk tickets. Shared proprietary Forge harness/scheduler/tools/lifecycle; score100×correct/graded. Tax tables in default SSR are a different evaluation and are never parsed as helpdesk. Metric: Correct ticket resolution (%). Source: https://evals.thriveholdings.com/?benchmark=it-helpdesk#it-helpdesk
Metric: Correct ticket resolution (%). Source: evals.thriveholdings.com. Saturation forecast: Around May 2028. 15 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6 Astra | xHigh | 61.54 | #6 |
| 2 | Claude Opus 5.5 | Max | 59.62 | #5 |
| 3 | GPT-6 Sol | Max | 55.77 | #26 |
| 4 | Claude Fable 5.1 | xHigh | 55.77 | #15 |
| 5 | Muse Spark 1.3 | xHigh | 51.92 | #43 |
| 6 | Claude Sonnet 5.5 | xHigh | 51.92 | #19 |
| 7 | GLM-5.3 | Max | 48.08 | #68 |
| 8 | Kimi K3 | Low | 48.08 | #56 |
| 9 | DeepSeek V4.1 Flash | Low | 48.08 | #62 |
| 10 | Grok 4.7 | High | 46.15 | #47 |
| 11 | GLM-5.3 Flash | Max | 42.31 | #125 |
| 12 | Gemini 3.8 Flash | High | 36.54 | #36 |
| 13 | GPT-6 Luna | xHigh | 34.62 | #99 |
| 14 | DeepSeek V4 Pro (0813) | xHigh | 32.69 | #90 |
| 15 | MiniMax-M3 | High | 23.08 | #272 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #10 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=thrive-helpdesk-difficult-tickets · How It Works · Data refreshed daily, snapshot 2026-11-16.