TeachArena
Agents make teaching decisions, tutor students through dialogue, and carry out learning management system tasks. The evaluator checks conversation turns, artifacts, and final system states.
- Released
- May 2026
- Kind
- Other professions
- Level
- University
- Scored
- Graded by a model
- Answers
- Agent task
- Measures
- Capability
- Subject
- Education
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Refresh
- One fixed set
- Run by
- A host
- Occupations
- Educational instruction and library
- In views
- Agents
- Strongest model tested
- GPT-5.5 Pro #15 on the capability index
- Last model added
- June 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 4.8 leads with 0.80 among models released by June 2026 Claude Opus 4.8 leads with 0.80 among models released by June 2026
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in June 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
- 0.80 Claude Opus 4.8
- 0.79 Claude Opus 4.6
- 0.78 GPT-5.5 Pro
- 0.76 GPT-5.5
- 0.75
Qwen3.7-Max
- 0.75 GLM-5.2
- 0.75
Qwen 3.6 Plus
- 0.73 GPT-5.4
- 0.73
DeepSeek-V4-Pro
- 0.73 GLM-5.1
- 0.72
Gemini 3.1 Pro
- 0.70 Gemini-2.5-pro (snapshot unspecified)
- 0.69
Gemini 3.5 Flash
- 0.69 Kimi K2.6
- 0.68
Qwen3-Max
- 0.67
Gemini 3.1 Flash-Lite
- 0.66 GPT-4.1
- 1 Claude Opus 4.8 0.80
- 2 Claude Opus 4.6 0.79
- 3 GPT-5.5 Pro 0.78
- 4 GPT-5.5 0.76
- 5
Qwen3.7-Max 0.75
- 6 GLM-5.2 0.75
- 7
Qwen 3.6 Plus 0.75
- 8 GPT-5.4 0.73
- 9
DeepSeek-V4-Pro 0.73
- 10 GLM-5.1 0.73
- 11
Gemini 3.1 Pro 0.72
- 12 Gemini-2.5-pro (snapshot unspecified) 0.70
- 13
Gemini 3.5 Flash 0.69
- 14 Kimi K2.6 0.69
- 15
Qwen3-Max 0.68
- 16
Gemini 3.1 Flash-Lite 0.67
- 17 GPT-4.1 0.66
Source: The TeachArena paper
- 1 Claude Opus 4.8 0.80
- 2 Claude Opus 4.6 0.79
- 3 GPT-5.5 Pro 0.78
- 4 GPT-5.5 0.76
- 5
Qwen3.7-Max 0.75
- 6 GLM-5.2 0.75
- 7
Qwen 3.6 Plus 0.75
- 8 GPT-5.4 0.73
- 9
DeepSeek-V4-Pro 0.73
- 10 GLM-5.1 0.73
- 11
Gemini 3.1 Pro 0.72
- 12
Gemini 3.5 Flash 0.69
- 13 Kimi K2.6 0.69
- 14
Qwen3-Max 0.68
- 15
Gemini 3.1 Flash-Lite 0.67
- 16 GPT-4.1 0.66
Source: The TeachArena paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 0.80 | May 2026 | Official leaderboard | |
| 2 | Claude Opus 4.6 | 0.79 | Feb 2026 | Official leaderboard | |
| 3 | GPT-5.5 Pro | 0.78 | Apr 2026 | Official leaderboard | |
| 4 | GPT-5.5 | 0.76 | Apr 2026 | Official leaderboard | |
| 5 | | 0.75 | May 2026 | Official leaderboard | |
| 6 | GLM-5.2 | 0.75 | Jun 2026 | Official leaderboard | |
| 7 | | 0.75 | Mar 2026 | Official leaderboard | |
| 8 | GPT-5.4 | 0.73 | Mar 2026 | Official leaderboard | |
| 9 | | 0.73 | Apr 2026 | Official leaderboard | |
| 10 | GLM-5.1 | 0.73 | Apr 2026 | Official leaderboard | |
| 11 | | 0.72 | Feb 2026 | Official leaderboard | |
| 12 | Gemini-2.5-pro (snapshot unspecified) | 0.70 | Official leaderboard | ||
| 13 | | 0.69 | May 2026 | Official leaderboard | |
| 14 | Kimi K2.6 | 0.69 | Apr 2026 | Official leaderboard | |
| 15 | | 0.68 | Sep 2025 | Official leaderboard | |
| 16 | | 0.67 | Mar 2026 | Official leaderboard | |
| 17 | GPT-4.1 | 0.66 | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 0.80 | May 2026 | Official leaderboard | |
| 2 | Claude Opus 4.6 | 0.79 | Feb 2026 | Official leaderboard | |
| 3 | GPT-5.5 Pro | 0.78 | Apr 2026 | Official leaderboard | |
| 4 | GPT-5.5 | 0.76 | Apr 2026 | Official leaderboard | |
| 5 | | 0.75 | May 2026 | Official leaderboard | |
| 6 | GLM-5.2 | 0.75 | Jun 2026 | Official leaderboard | |
| 7 | | 0.75 | Mar 2026 | Official leaderboard | |
| 8 | GPT-5.4 | 0.73 | Mar 2026 | Official leaderboard | |
| 9 | | 0.73 | Apr 2026 | Official leaderboard | |
| 10 | GLM-5.1 | 0.73 | Apr 2026 | Official leaderboard | |
| 11 | | 0.72 | Feb 2026 | Official leaderboard | |
| 12 | | 0.69 | May 2026 | Official leaderboard | |
| 13 | Kimi K2.6 | 0.69 | Apr 2026 | Official leaderboard | |
| 14 | | 0.68 | Sep 2025 | Official leaderboard | |
| 15 | | 0.67 | Mar 2026 | Official leaderboard | |
| 16 | GPT-4.1 | 0.66 | Apr 2025 | Official leaderboard |
2 models have held number one in the benchmark’s paper since its release in May 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The TeachArena paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official TeachArena 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 Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (17 entries).
- Pass Models scored 16 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from June 2026, for GLM-5.2.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 Pro (#15).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 16 rows for models we track and 1 other entry 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.