Benchmark Almanac

TalentCLEF 2026 Contextualized Job-Person Matching

JobBERT-v3 + KaLM-12B + Octen-8B + Nemotron-8B + ZEmbed1-4B + Harrier-27B + gemini-embedding-001 + GPT-5.5 + Claude Opus 4.6 + Gemini 3 Flash + Cohere-rerank-4 + zerank-2 0.71 tops its leaderboard
Not in model cards

Models rank candidate resumes for a job description in English or Spanish. Organizers score retrieval within and across languages and compare rankings across gender variants.

Classum used GPT-5.5 and Claude Opus 4.6 in its winning system. Its mean average precision was 0.7122 in English and 0.7157 in Spanish.

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, Spanish
In and out
Text → Text
Interaction
Single turn
Items from
Generated
Run by
A host
In views
Law and finance
13
Entries on its own leaderboard, 0 models we track

JobBERT-v3 + KaLM-12B + Octen-8B + Nemotron-8B + ZEmbed1-4B + Harrier-27B + gemini-embedding-001 + GPT-5.5 + Claude Opus 4.6 + Gemini 3 Flash + Cohere-rerank-4 + zerank-2 tops the leaderboard with 0.71

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 JobBERT-v3 + KaLM-12B + Octen-8B + Nemotron-8B + ZEmbed1-4B + Harrier-27B + gemini-embedding-001 + GPT-5.5 + Claude Opus 4.6 + Gemini 3 Flash + Cohere-rerank-4 + zerank-2 715941 0.71
  2. 2 QTPride 696980 0.66
  3. 3 Qwen3-Reranker-8B + Qwen3-235B + BGE-LoRA + MiniLM 715693 0.65
  4. 4 multilingual-e5-large-instruct + BM25 + Mistral + Jina cross-encoder v2 709705 0.65
  5. 5 multilingual-e5-large-instruct + bge-large-en-v1.5 + BM25 + ms-marco-MiniLM-L12-v2 cross-encoder 715491 0.63
  6. 6 bge-m3 + Gemma 3 27B + BM25 702458 0.61
  7. 7 BM25 + BGE-M3 + SkillMatch MPNet + GPT-5.2 999999 0.60
  8. 8 JobBERT + JobBERT-v3 + RoBERTa 715595 0.56
  9. 9 bge-m3 + BM25 + mMiniLMv2 cross-encoder 710446 0.56
  10. 10 hr_gradient 716035 0.53
  11. 11 JobBERT-v3 + SPLADE + jina-colbert-v2 699840 0.51
  12. 12 paraphrase-multilingual-MiniLM-L12-v2 + doc2query-t5-base-msmarco + BM25 701328 0.49
  13. 13 TalentCLEF baseline 690133 0.38

Source: Official TalentCLEF 2026 Contextualized Job-Person Matching leaderboard

#EntryScoreSettingSubmitted byDateSource
1 JobBERT-v3 + KaLM-12B + Octen-8B + Nemotron-8B + ZEmbed1-4B + Harrier-27B + gemini-embedding-001 + GPT-5.5 + Claude Opus 4.6 + Gemini 3 Flash + Cohere-rerank-4 + zerank-2 0.71 715941 classum Official leaderboard
2 QTPride 0.66 696980 QTPride Official leaderboard
3 Qwen3-Reranker-8B + Qwen3-235B + BGE-LoRA + MiniLM 0.65 715693 bipboopbipboop Official leaderboard
4 multilingual-e5-large-instruct + BM25 + Mistral + Jina cross-encoder v2 0.65 709705 Skillberg Official leaderboard
5 multilingual-e5-large-instruct + bge-large-en-v1.5 + BM25 + ms-marco-MiniLM-L12-v2 cross-encoder 0.63 715491 ui-nlp Official leaderboard
6 bge-m3 + Gemma 3 27B + BM25 0.61 702458 CYUT Official leaderboard
7 BM25 + BGE-M3 + SkillMatch MPNet + GPT-5.2 0.60 999999 DevoMatcher Official leaderboard
8 JobBERT + JobBERT-v3 + RoBERTa 0.56 715595 HR_NLP Official leaderboard
9 bge-m3 + BM25 + mMiniLMv2 cross-encoder 0.56 710446 VerbaNex Official leaderboard
10 hr_gradient 0.53 716035 hr_gradient Official leaderboard
11 JobBERT-v3 + SPLADE + jina-colbert-v2 0.51 699840 qwerity Official leaderboard
12 paraphrase-multilingual-MiniLM-L12-v2 + doc2query-t5-base-msmarco + BM25 0.49 701328 UBCS Official leaderboard
13 TalentCLEF baseline 0.38 690133 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.

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 (13 entries).
  • Pass Models scored 13 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: 13 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