Benchmark Almanac

TalentCLEF 2026 Job-Skill Matching with Skill Type Classification

ZEmbed1-4B + KaLM-12B + Qwen3-8B + NVEmbed-3B + Zerank2 0.81 tops its leaderboard
Not in model cards
Version 2026

Models rank skills for an English job title. The main ranking metric gives core skills more weight than contextual skills.

The official results include 19 runs. Classum used Qwen3-8B in the winning system and scored 0.8068 under graded relevance.

Released
November 2025
Kind
Other professions
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Run by
A host
In views
Law and finance
10
Entries on its own leaderboard, 0 models we track

ZEmbed1-4B + KaLM-12B + Qwen3-8B + NVEmbed-3B + Zerank2 tops the leaderboard with 0.81

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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.

  1. 1 ZEmbed1-4B + KaLM-12B + Qwen3-8B + NVEmbed-3B + Zerank2 715319, Retrieval+Reranking, Augmentation 0.81
  2. 2 JobBERT-v2 + Qwen-2.5-7B-Instruct-AWQ 709648, Retrieval+Reranking, Reranking + augmentation 0.79
  3. 3 Qwen3-Embedding-4B + Qwen3-Reranker-8B + Qwen3-235B-A22B-Instruct + JobBERT-v3 714675, Retrieval+Reranking, Reranking + augmentation 0.78
  4. 4 Alibaba-NLP/gte-modernbert-base + Qwen/Qwen3-Reranker-0.6B + Gemma 4 716124, Retrieval+Reranking, Augmentation 0.74
  5. 5 Skillberg 710631, Retrieval, None 0.71
  6. 6 baorphuc 692732, Retrieval, None 0.68
  7. 7 ui-nlp 716152, Retrieval, None 0.68
  8. 8 BM25 + intfloat/e5-base-v2 697840, Retrieval, None 0.65
  9. 9 BM25 + BAAI/bge-base-en-v1.5 + paraphrase-multilingual-mpnet-base-v2 693022, Retrieval, None 0.65
  10. 10 TalentCLEF baseline 690199 0.62

Source: Official TalentCLEF 2026 Job-Skill Matching with Skill Type Classification leaderboard

#EntryScoreSettingSubmitted byDateSource
1 ZEmbed1-4B + KaLM-12B + Qwen3-8B + NVEmbed-3B + Zerank2 0.81 715319, Retrieval+Reranking, Augmentation, classum classum Official leaderboard
2 JobBERT-v2 + Qwen-2.5-7B-Instruct-AWQ 0.79 709648, Retrieval+Reranking, Reranking + augmentation, NightSun NightSun Official leaderboard
3 Qwen3-Embedding-4B + Qwen3-Reranker-8B + Qwen3-235B-A22B-Instruct + JobBERT-v3 0.78 714675, Retrieval+Reranking, Reranking + augmentation, bipboopbipboop bipboopbipboop Official leaderboard
4 Alibaba-NLP/gte-modernbert-base + Qwen/Qwen3-Reranker-0.6B + Gemma 4 0.74 716124, Retrieval+Reranking, Augmentation, hr_gradient hr_gradient Official leaderboard
5 Skillberg 0.71 710631, Retrieval, None, Skillberg Skillberg Official leaderboard
6 baorphuc 0.68 692732, Retrieval, None, baorphuc baorphuc Official leaderboard
7 ui-nlp 0.68 716152, Retrieval, None, ui-nlp ui-nlp Official leaderboard
8 BM25 + intfloat/e5-base-v2 0.65 697840, Retrieval, None, MARSAD MARSAD Official leaderboard
9 BM25 + BAAI/bge-base-en-v1.5 + paraphrase-multilingual-mpnet-base-v2 0.65 693022, Retrieval, None, Olive Olive Official leaderboard
10 TalentCLEF baseline 0.62 690199, TalentCLEF baseline TalentCLEF baseline Official 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.

Versions

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

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 10 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on talentclef.github.io: 10 entries at the last read, none a model we track.
  • 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