Benchmark Almanac

SLATE

Claude Opus 4.7 5.46% leads since September 2026
Not in model cards

Models generate slides that teach unfamiliar language patterns. Simulated learners take tests before and after the lesson and apply the rules to new examples.

Released
September 2026
Kind
Other professions
Level
University
Scored
Checked automatically
Answers
Open-ended
Measures
Capability
Language
Many languages
In and out
Text → Documents
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
A host
In views
Many languages
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
10
Models scored in its paper

Claude Opus 4.7 leads with 5.46% 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. Table 3 ranks models by D4 gain, the change in learner accuracy from pretest to posttest in percentage points. 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 5.46%
  2. 2 Qwen 3.6 Max (Preview) 5.14%
  3. 3 MiniMax-M2.7 3.27%
  4. 4 GPT-5.4 2.61%
  5. 5 Claude Sonnet 4.6 1.85%
  6. 6 Qwen 3.6 Plus 0.38%
  7. 7 Kimi K2.6 -0.89%
  8. 8 GLM-5.1 -1.24%
  9. 9 DeepSeek-V4-Pro -1.68%
  10. 10 Gemini 3.1 Pro -2.51%

Source: The SLATE paper

#ModelScoreSettingDateSource
1 Claude Opus 4.7 5.46% Apr 2026 Official leaderboard
2 Qwen 3.6 Max (Preview) 5.14% Apr 2026 Official leaderboard
3 MiniMax-M2.7 3.27% Mar 2026 Official leaderboard
4 GPT-5.4 2.61% Mar 2026 Official leaderboard
5 Claude Sonnet 4.6 1.85% Feb 2026 Official leaderboard
6 Qwen 3.6 Plus 0.38% Mar 2026 Official leaderboard
7 Kimi K2.6 -0.89% Apr 2026 Official leaderboard
8 GLM-5.1 -1.24% Apr 2026 Official leaderboard
9 DeepSeek-V4-Pro -1.68% Apr 2026 Official leaderboard
10 Gemini 3.1 Pro -2.51% Feb 2026 Official leaderboard

Rankings by part

We read 7 parts from the benchmark’s paper, each ranking models on one part of the test, such as Paradigm completion, Translation and Morphology. Qwen 3.6 Max (Preview) leads 2 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Paradigm completion

10 models we track have a score here.

  1. 1 Qwen 3.6 Max (Preview) ↑1 9.40%
  2. 2 Claude Opus 4.7 ↓1 8.50%
  3. 3 MiniMax-M2.7 7.90%
  4. 4 Claude Sonnet 4.6 ↑1 4.70%
  5. 5 GPT-5.4 ↓1 4.50%
  6. 6 Qwen 3.6 Plus 3.00%
  7. 7 GLM-5.1 ↑1 0.80%
  8. 8 Kimi K2.6 ↓1 0%
  9. 9 DeepSeek-V4-Pro -1.20%
  10. 10 Gemini 3.1 Pro -2.90%

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 Sep 2026

Source: The SLATE 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% 2026 Near the ceiling (85%) Claude Opus 4.7 GPT-5.4 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.7

Source: Official SLATE 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 10 checks pass, 2 warnings. 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 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (10 entries).
  • Pass Models scored 10 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-5.4 (#28).
  • Pass Headroom The best is 5.46%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 10 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