Thrive Holdings helpdesk ticket resolution benchmark
GPT-6 Astra 61.5% leads since October 2026
Not in model cards Agent investigates IT support requests, takes action and decides when to escalate to a technician. Scored by pass rate.
Item count not stated. Drawn from Thrive's IT services firms.
- Made by
- Thrive Holdings
- Released
- October 2026
- Kind
- Tasks from real jobs
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Strongest model tested
- GPT-6 Astra #3 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 12th, 2026
15
Models scored on its own leaderboard
GPT-6 Astra leads with 61.5% among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6.1 Sol
- GPT-6.1 Terra
- and 11 more
- 1 GPT-6 Astra xhigh 61.5%
- 2 Claude Opus 5.5 max 59.6%
- 3 Claude Fable 5.1 xhigh 55.8%
- 4 GPT-6 Sol max 55.8%
- 5
Muse Spark 1.3 xhigh 51.9% - 6 Claude Sonnet 5.5 xhigh 51.9%
- 7 Kimi K3 low 48.1%
- 8 GLM-5.3 max 48.1%
- 9
DeepSeek V4.1 Flash low 48.1% - 10 Grok 4.7 high 46.1%
- 11 GLM-5.3-Flash max 42.3%
- 12 Gemini 3.8 Flash high 36.5%
- 13 GPT-6 Luna xhigh 34.6%
- 14 DeepSeek V4 Pro 0813 xhigh 32.7%
- 15
MiniMax-M3 high 23.1%
Source: Official Thrive Holdings helpdesk ticket resolution benchmark leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 61.5% | xhigh | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 59.6% | max | Sep 2026 | Official leaderboard |
| 3 | Claude Fable 5.1 | 55.8% | xhigh | Sep 2026 | Official leaderboard |
| 4 | GPT-6 Sol | 55.8% | max | Sep 2026 | Official leaderboard |
| 5 | Muse Spark 1.3 | 51.9% | xhigh | Sep 2026 | Official leaderboard |
| 6 | Claude Sonnet 5.5 | 51.9% | xhigh | Sep 2026 | Official leaderboard |
| 7 | Kimi K3 | 48.1% | low | Jul 2026 | Official leaderboard |
| 8 | GLM-5.3 | 48.1% | max | Aug 2026 | Official leaderboard |
| 9 | DeepSeek V4.1 Flash | 48.1% | low | Sep 2026 | Official leaderboard |
| 10 | Grok 4.7 | 46.1% | high | Sep 2026 | Official leaderboard |
| 11 | GLM-5.3-Flash | 42.3% | max | Aug 2026 | Official leaderboard |
| 12 | Gemini 3.8 Flash | 36.5% | high | Sep 2026 | Official leaderboard |
| 13 | GPT-6 Luna | 34.6% | xhigh | Sep 2026 | Official leaderboard |
| 14 | DeepSeek V4 Pro 0813 | 32.7% | xhigh | Aug 2026 | Official leaderboard |
| 15 | MiniMax-M3 | 23.1% | high | Jun 2026 | Official leaderboard |
Performance, cost & time
Each point is one model at one reasoning effort: pass rate against the minutes it takes to resolve one ticket, with the Pareto frontier. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Pass rate | Minutes per ticket |
|---|---|---|---|
| GPT-6 Astra | xhigh | 61.5% | 19.86 min |
| GPT-6 Astra | high | 59.6% | 16.93 min |
| Claude Opus 5.5 | max | 59.6% | 22.39 min |
| GPT-6 Astra | low | 57.7% | 9.68 min |
| Claude Opus 5.5 | xhigh | 57.7% | 16.9 min |
| Claude Fable 5.1 | xhigh | 55.8% | 21.05 min |
| GPT-6 Sol | max | 55.8% | 25.21 min |
| GPT-6 Astra | medium | 53.9% | 12.86 min |
| Claude Opus 5.5 | high | 53.9% | 12.99 min |
| Claude Fable 5.1 | high | 53.9% | 14.85 min |
| GPT-6 Astra | max | 53.9% | 23.76 min |
| Muse Spark 1.3 | xhigh | 51.9% | 16.17 min |
| GPT-6 Sol | xhigh | 51.9% | 19.77 min |
| Claude Sonnet 5.5 | xhigh | 51.9% | 22.69 min |
| Claude Opus 5.5 | medium | 50% | 8.95 min |
| GPT-6 Sol | high | 50% | 15.96 min |
| Claude Fable 5.1 | max | 50% | 26.11 min |
| Claude Sonnet 5.5 | high | 48.1% | 9.97 min |
| Kimi K3 | low | 48.1% | 11.55 min |
| Claude Fable 5.1 | medium | 48.1% | 13.21 min |
| DeepSeek V4.1 Flash | low | 48.1% | 14.87 min |
| GLM-5.3 | max | 48.1% | 26.83 min |
| GPT-6 Sol | low | 46.2% | 7.76 min |
| Claude Fable 5.1 | low | 46.2% | 11.54 min |
| GPT-6 Sol | medium | 46.2% | 11.73 min |
| Grok 4.7 | high | 46.2% | 24.01 min |
| Claude Sonnet 5.5 | max | 46.2% | 25.52 min |
| Kimi K3 | high | 44.2% | 10.64 min |
| Muse Spark 1.3 | high | 42.3% | 13.38 min |
| Kimi K3 | max | 42.3% | 14.67 min |
| GLM-5.3-Flash | max | 42.3% | 16.17 min |
| Grok 4.7 | medium | 42.3% | 19.81 min |
| DeepSeek V4.1 Flash | max | 42.3% | 28.82 min |
| Muse Spark 1.3 | medium | 40.4% | 12.73 min |
| Claude Opus 5.5 | low | 38.5% | 4.43 min |
| GLM-5.3 | high | 38.5% | 11.78 min |
| DeepSeek V4.1 Flash | high | 38.5% | 21.93 min |
| Muse Spark 1.3 | low | 36.5% | 8.54 min |
| Muse Spark 1.3 | max | 36.5% | 23.25 min |
| Gemini 3.8 Flash | high | 36.5% | 24.45 min |
| Claude Sonnet 5.5 | medium | 34.6% | 6.82 min |
| Grok 4.7 | low | 34.6% | 12.03 min |
| Gemini 3.8 Flash | medium | 34.6% | 19.26 min |
| GPT-6 Luna | xhigh | 34.6% | 19.44 min |
| GLM-5.3 | low | 32.7% | 9.54 min |
| GLM-5.3-Flash | high | 32.7% | 10.62 min |
| DeepSeek V4 Pro 0813 | xhigh | 32.7% | 12.88 min |
| Claude Sonnet 5.5 | low | 30.8% | 4.08 min |
| Gemini 3.8 Flash | low | 30.8% | 12.43 min |
| GPT-6 Luna | high | 30.8% | 15.63 min |
| GPT-6 Luna | max | 30.8% | 27.73 min |
| DeepSeek V4 Pro 0813 | high | 28.9% | 14 min |
| Grok 4.7 | xhigh | 28.9% | 29.44 min |
| GLM-5.3-Flash | low | 26.9% | 6.81 min |
| GPT-6 Luna | medium | 26.9% | 12.8 min |
| MiniMax-M3 | high | 23.1% | 11.58 min |
| GPT-6 Luna | low | 19.2% | 7.32 min |
The best score, 61.5%, costs $7.63 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Meta OpenAI DeepSeek Anthropic
Cost frontier
One model at each effort level
Source: Official Thrive Holdings helpdesk ticket resolution benchmark leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-6 Astra | xhigh | 61.5% | $7.63 | ||
| GPT-6 Astra | high | 59.6% | $7.09 | ||
| Claude Opus 5.5 | max | 59.6% | $8.25 | ||
| GPT-6 Astra | low | 57.7% | $5.12 | ||
| Claude Opus 5.5 | xhigh | 57.7% | $4.13 | ||
| Claude Fable 5.1 | xhigh | 55.8% | $14 | ||
| GPT-6 Sol | max | 55.8% | $2.25 | ||
| Claude Fable 5.1 | high | 53.9% | $11 | ||
| GPT-6 Astra | medium | 53.9% | $6.04 | ||
| GPT-6 Astra | max | 53.9% | $8.36 | ||
| Claude Opus 5.5 | high | 53.9% | $3.26 | ||
| Muse Spark 1.3 | xhigh | 51.9% | $1.42 | ||
| GPT-6 Sol | xhigh | 51.9% | $1.77 | ||
| Claude Sonnet 5.5 | xhigh | 51.9% | $2.46 | ||
| Claude Fable 5.1 | max | 50% | $18 | ||
| Claude Opus 5.5 | medium | 50% | $2.89 | ||
| GPT-6 Sol | high | 50% | $1.45 | ||
| Kimi K3 | low | 48.1% | $1.79 | ||
| GLM-5.3 | max | 48.1% | $1.48 | ||
| Claude Fable 5.1 | medium | 48.1% | $9.80 | ||
| DeepSeek V4.1 Flash | low | 48.1% | $0.13 | ||
| Claude Sonnet 5.5 | high | 48.1% | $1.50 | ||
| Claude Fable 5.1 | low | 46.1% | $9.37 | ||
| Grok 4.7 | high | 46.1% | $3.51 | ||
| GPT-6 Sol | low | 46.1% | $0.97 | ||
| GPT-6 Sol | medium | 46.1% | $1.18 | ||
| Claude Sonnet 5.5 | max | 46.1% | $6.20 | ||
| Kimi K3 | high | 44.2% | $1.65 | ||
| Kimi K3 | max | 42.3% | $1.89 | ||
| GLM-5.3-Flash | max | 42.3% | $0.20 | ||
| Muse Spark 1.3 | high | 42.3% | $2.03 | ||
| DeepSeek V4.1 Flash | max | 42.3% | $0.20 | ||
| Grok 4.7 | medium | 42.3% | $3.06 | ||
| Muse Spark 1.3 | medium | 40.4% | $1.89 | ||
| GLM-5.3 | high | 38.5% | $1.14 | ||
| DeepSeek V4.1 Flash | high | 38.5% | $0.14 | ||
| Claude Opus 5.5 | low | 38.5% | $2.33 | ||
| Gemini 3.8 Flash | high | 36.5% | $1.59 | ||
| Muse Spark 1.3 | low | 36.5% | $1.74 | ||
| Muse Spark 1.3 | max | 36.5% | $2.47 | ||
| Gemini 3.8 Flash | medium | 34.6% | $1.15 | ||
| Grok 4.7 | low | 34.6% | $2.28 | ||
| GPT-6 Luna | xhigh | 34.6% | $0.09 | ||
| Claude Sonnet 5.5 | medium | 34.6% | $1.23 | ||
| DeepSeek V4 Pro 0813 | xhigh | 32.7% | $0.53 | ||
| GLM-5.3 | low | 32.7% | $0.80 | ||
| GLM-5.3-Flash | high | 32.7% | $0.16 | ||
| Gemini 3.8 Flash | low | 30.8% | $0.84 | ||
| GPT-6 Luna | high | 30.8% | $0.08 | ||
| GPT-6 Luna | max | 30.8% | $0.13 | ||
| Claude Sonnet 5.5 | low | 30.8% | $1.23 | ||
| DeepSeek V4 Pro 0813 | high | 28.9% | $0.53 | ||
| Grok 4.7 | xhigh | 28.9% | $4.31 | ||
| GLM-5.3-Flash | low | 26.9% | $0.13 | ||
| GPT-6 Luna | medium | 26.9% | $0.07 | ||
| MiniMax-M3 | high | 23.1% | $0.27 | ||
| GPT-6 Luna | low | 19.2% | $0.05 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
OpenAI
Source: Official Thrive Holdings helpdesk ticket resolution benchmark leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
On the benchmark’s own leaderboard
Best so far
Source: Official Thrive Holdings helpdesk ticket resolution benchmark leaderboard
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9% - GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
- OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%