Benchmark Almanac

ELBench

DeepSeek-V4-Flash 83.5 leads since June 2026
Not in model cards

Models respond to teaching and safety scenarios alongside academic questions. The authors compare the same models across four educational assessment areas.

Made by
Yilin Jiang and colleagues
Released
June 2026
Kind
Other professions
Level
University
Scored
Graded by a model
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Subject
Education
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Strongest model tested
Claude Opus 4.8 #22 on the capability index
Last model added
May 2026
Scores refreshed
November 20th, 2026
9
Entries in its paper, 7 models we track

DeepSeek-V4-Flash leads with 83.5 among models released by May 2026 DeepSeek-V4-Flash leads with 83.5 among models released by May 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 May 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 DeepSeek-V4-Flash 83.5
  2. 2 DeepSeek-V4-Pro 82.9
  3. 3 Seed2.0 Pro 82.8
  4. 4 Gemini 3.5 Flash 82.7
  5. 5 GPT-5.4 82.6
  6. 6 Claude Opus 4.8 82.5
  7. 7 GLM-5.1 81.6
  8. 8 safe-innospark 76.9
  9. 9 innospark-235b 75.9

Source: The ELBench paper

#EntryScoreSettingDateSource
1 DeepSeek-V4-Flash 83.5 Apr 2026 Official leaderboard
2 DeepSeek-V4-Pro 82.9 Apr 2026 Official leaderboard
3 Seed2.0 Pro 82.8 Feb 2026 Official leaderboard
4 Gemini 3.5 Flash 82.7 May 2026 Official leaderboard
5 GPT-5.4 82.6 Mar 2026 Official leaderboard
6 Claude Opus 4.8 82.5 May 2026 Official leaderboard
7 GLM-5.1 81.6 Apr 2026 Official leaderboard
8 safe-innospark 76.9 Official leaderboard
9 innospark-235b 75.9 Official leaderboard
#ModelScoreSettingDateSource
1 DeepSeek-V4-Flash 83.5 Apr 2026 Official leaderboard
2 DeepSeek-V4-Pro 82.9 Apr 2026 Official leaderboard
3 Seed2.0 Pro 82.8 Feb 2026 Official leaderboard
4 Gemini 3.5 Flash 82.7 May 2026 Official leaderboard
5 GPT-5.4 82.6 Mar 2026 Official leaderboard
6 Claude Opus 4.8 82.5 May 2026 Official leaderboard
7 GLM-5.1 81.6 Apr 2026 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s paper, each ranking models on one part of the test, such as General Capability, Safety and Trustworthiness and Basic Education. Gemini 3.5 Flash leads 3 of them, and DeepSeek-V4-Flash leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

General Capability

7 models we track have a score here.

  1. 1 Gemini 3.5 Flash ↑3 93.4
  2. 2 Claude Opus 4.8 ↑4 91.9
  3. 3 DeepSeek-V4-Flash ↓2 88.5
  4. 4 DeepSeek-V4-Pro ↓2 88.2
  5. 5 Seed2.0 Pro ↓2 86.6
  6. 6 GPT-5.4 ↓1 86.4
  7. 7 GLM-5.1 83.2

Number one over time

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

DeepSeek
Benchmark paper Not tested since Jun 2026

Source: The ELBench 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
81.5 82.0 82.5 83.0 83.5 84.0 2026 81.5 82.0 82.5 83.0 83.5 84.0 2026

Source: Official ELBench 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 Newest score check. The newest came 6 months ago, in May 2026, for Claude Opus 4.8. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 7 models we track, plus 2 other entries on its leaderboard.
  • Warning Newest score The newest came 6 months ago, in May 2026, for Claude Opus 4.8.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 4.8 (#22).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 7 rows for models we track and 2 other entries 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