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

#ModelSettingScoreOverall rank
1GPT-6 AstraxHigh61.54#6
2Claude Opus 5.5Max59.62#5
3GPT-6 SolMax55.77#26
4Claude Fable 5.1xHigh55.77#15
5Muse Spark 1.3xHigh51.92#43
6Claude Sonnet 5.5xHigh51.92#19
7GLM-5.3Max48.08#68
8Kimi K3Low48.08#56
9DeepSeek V4.1 FlashLow48.08#62
10Grok 4.7High46.15#47
11GLM-5.3 FlashMax42.31#125
12Gemini 3.8 FlashHigh36.54#36
13GPT-6 LunaxHigh34.62#99
14DeepSeek V4 Pro (0813)xHigh32.69#90
15MiniMax-M3High23.08#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.