Long-Horizon Medical Agent Benchmark, Veterinary Clinic Ops v2
Agents operate a simulated veterinary clinic through its database API. Each of the 98 tasks checks whether the agent leaves the clinic records in the required state.
The highest public hub mean reward was 1 for gpt-5.6-luna on 100 examples on September 3rd, 2026. The hub also lists gpt-5.6-sol, grok-4.6, gemini-3.7-flash.
- Released
- September 2026
- Kind
- Tasks from real jobs
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Veterinary science
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools, A simulator
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- Strongest model tested
- GPT-5.6 Sol #14 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
GPT-5.6 Sol leads with 100% among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 15 more
- 1 GPT-5.6 Sol 100%
- 2 Grok 4.6 80%
- 3 GLM-5.3-Flash 80%
- 4
DeepSeek-V4-Flash 12%
- 5
Qwen 3.8 Max 8.00%
- 6 gpt-oss-120b 0%
- 7
Gemini 3.8 Flash 0%
Source: Official Long-Horizon Medical Agent Benchmark, Veterinary Clinic Ops v2 leaderboard
| # | Model | Score | Setting | Submitted by | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-5.6 Sol | 100% | verifiers | praesidiumsystems | Jul 2026 | Sep 2026 | app.primeintellect.ai | Official leaderboard |
| 2 | Grok 4.6 | 80% | verifiers | praesidiumsystems | Aug 2026 | Sep 2026 | app.primeintellect.ai | Official leaderboard |
| 3 | GLM-5.3-Flash | 80% | verifiers | praesidiumsystems | Aug 2026 | Sep 2026 | app.primeintellect.ai | Official leaderboard |
| 4 | | 12% | verifiers | praesidiumsystems | Apr 2026 | Sep 2026 | app.primeintellect.ai | Official leaderboard |
| 5 | | 8.00% | verifiers | praesidiumsystems | Aug 2026 | Sep 2026 | app.primeintellect.ai | Official leaderboard |
| 6 | gpt-oss-120b | 0% | verifiers | praesidiumsystems | Aug 2025 | Sep 2026 | app.primeintellect.ai | Official leaderboard |
| 7 | | 0% | praesidiumsystems | Sep 2026 | Sep 2026 | app.primeintellect.ai | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Long-Horizon Medical Agent Benchmark, Veterinary Clinic Ops v2 leaderboard
GPT-5.6 Sol on the official leaderboard passed 85% in July 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Long-Horizon Medical Agent Benchmark, Veterinary Clinic Ops v2 leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 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
- Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
- 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%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 7 models we track.
- Pass Newest score The newest is from September 2026, for Gemini 3.8 Flash.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.6 Sol (#14).
- Note Headroom Saturated. The best is 100%, past 85% since July 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on app.primeintellect.ai: 7 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.