Benchmark Almanac

TeachArena

Claude Opus 4.8 0.80 leads since May 2026
Not in model cards

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
In and out
Text → Text, Actions
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
17
Entries in its paper, 16 models we track

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:

  1. 1 Claude Opus 4.8 0.80
  2. 2 Claude Opus 4.6 0.79
  3. 3 GPT-5.5 Pro 0.78
  4. 4 GPT-5.5 0.76
  5. 5 Qwen3.7-Max 0.75
  6. 6 GLM-5.2 0.75
  7. 7 Qwen 3.6 Plus 0.75
  8. 8 GPT-5.4 0.73
  9. 9 DeepSeek-V4-Pro 0.73
  10. 10 GLM-5.1 0.73
  11. 11 Gemini 3.1 Pro 0.72
  12. 12 Gemini-2.5-pro (snapshot unspecified) 0.70
  13. 13 Gemini 3.5 Flash 0.69
  14. 14 Kimi K2.6 0.69
  15. 15 Qwen3-Max 0.68
  16. 16 Gemini 3.1 Flash-Lite 0.67
  17. 17 GPT-4.1 0.66

Source: The TeachArena paper

#EntryScoreSettingDateSource
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 Qwen3.7-Max 0.75 May 2026 Official leaderboard
6 GLM-5.2 0.75 Jun 2026 Official leaderboard
7 Qwen 3.6 Plus 0.75 Mar 2026 Official leaderboard
8 GPT-5.4 0.73 Mar 2026 Official leaderboard
9 DeepSeek-V4-Pro 0.73 Apr 2026 Official leaderboard
10 GLM-5.1 0.73 Apr 2026 Official leaderboard
11 Gemini 3.1 Pro 0.72 Feb 2026 Official leaderboard
12 Gemini-2.5-pro (snapshot unspecified) 0.70 Official leaderboard
13 Gemini 3.5 Flash 0.69 May 2026 Official leaderboard
14 Kimi K2.6 0.69 Apr 2026 Official leaderboard
15 Qwen3-Max 0.68 Sep 2025 Official leaderboard
16 Gemini 3.1 Flash-Lite 0.67 Mar 2026 Official leaderboard
17 GPT-4.1 0.66 Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
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 Qwen3.7-Max 0.75 May 2026 Official leaderboard
6 GLM-5.2 0.75 Jun 2026 Official leaderboard
7 Qwen 3.6 Plus 0.75 Mar 2026 Official leaderboard
8 GPT-5.4 0.73 Mar 2026 Official leaderboard
9 DeepSeek-V4-Pro 0.73 Apr 2026 Official leaderboard
10 GLM-5.1 0.73 Apr 2026 Official leaderboard
11 Gemini 3.1 Pro 0.72 Feb 2026 Official leaderboard
12 Gemini 3.5 Flash 0.69 May 2026 Official leaderboard
13 Kimi K2.6 0.69 Apr 2026 Official leaderboard
14 Qwen3-Max 0.68 Sep 2025 Official leaderboard
15 Gemini 3.1 Flash-Lite 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.

Anthropic
Benchmark paper Not tested since Jun 2026

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.

Plot with other benchmarks
In the benchmark’s paper
0.65 0.70 0.75 0.80 0.85 2025 2026 0.65 0.70 0.75 0.80 0.85 2025 2026

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

All 637 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.

How we check