Benchmark Almanac

TutorCaseBench

Claude Opus 4.7 59.4% leads since October 2026
Not in model cards

Tutors respond to students whose behavior interferes with learning. Case-specific rubrics grade the responses, and a separate track tests selection among possible interventions.

Released
October 2026
Kind
Other professions
Level
University
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Occupations
Educational instruction and library
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
11
Models scored in its paper

Claude Opus 4.7 leads with 59.4% among models released by April 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of open-ended success and multiple-choice accuracy. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in April 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 4.7 59.4%
  2. 2 GPT-5.5 58.5%
  3. 3 Gemini 3.1 Pro 57.4%
  4. 4 Claude Haiku 4.5 52.5%
  5. 5 Gemini 3 Flash 51.1%
  6. 6 DeepSeek-V4-Pro 50.2%
  7. 7 Gemma 4 31B IT 49.4%
  8. 8 Qwen3.5 397B-A17B 48.1%
  9. 9 GPT-5.4 Mini 47.4%
  10. 10 gpt-oss-120b 46.8%
  11. 11 Llama 4 Maverick 41.7%

Source: The TutorCaseBench paper

#ModelScoreSettingDateSource
1 Claude Opus 4.7 59.4% Apr 2026 Official leaderboard
2 GPT-5.5 58.5% Apr 2026 Official leaderboard
3 Gemini 3.1 Pro 57.4% Feb 2026 Official leaderboard
4 Claude Haiku 4.5 52.5% Oct 2025 Official leaderboard
5 Gemini 3 Flash 51.1% Dec 2025 Official leaderboard
6 DeepSeek-V4-Pro 50.2% Apr 2026 Official leaderboard
7 Gemma 4 31B IT 49.4% Apr 2026 Official leaderboard
8 Qwen3.5 397B-A17B 48.1% Feb 2026 Official leaderboard
9 GPT-5.4 Mini 47.4% Mar 2026 Official leaderboard
10 gpt-oss-120b 46.8% Aug 2025 Official leaderboard
11 Llama 4 Maverick 41.7% Apr 2025 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s paper in 2 groups: open-ended response and 4-option mcq. Each ranks models on one part of the test. Claude Opus 4.7 leads 4 of them, and Gemini 3.1 Pro leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

Open-ended response

11 models we track have a score here.

  1. 1 Claude Opus 4.7 55.8%
  2. 2 GPT-5.5 54.7%
  3. 3 Gemini 3.1 Pro 52.2%
  4. 4 Claude Haiku 4.5 50.1%
  5. 5 DeepSeek-V4-Pro ↑1 47%
  6. 6 Gemini 3 Flash ↓1 46.2%
  7. 7 gpt-oss-120b ↑3 44.3%
  8. 8 GPT-5.4 Mini ↑1 41.7%
  9. 9 Gemma 4 31B IT ↓2 41.4%
  10. 10 Qwen3.5 397B-A17B ↓2 40.3%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Benchmark paper Not tested since Oct 2026

Source: The TutorCaseBench 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 Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Opus 4.7 Claude Haiku 4.5 gpt-oss-120b Llama 4 Maverick 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Opus 4.7 Claude Haiku 4.5

Source: Official TutorCaseBench 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for DeepSeek-V4-Pro. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (11 entries).
  • Pass Models scored 11 models we track.
  • Warning Newest score The newest came 7 months ago, in April 2026, for DeepSeek-V4-Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Pass Headroom The best is 59.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 11 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.

How we check