# Leaderboards for AI models Which model leads at which task – with the cheapest price in the EU and worldwide, open weights and the GPU memory for self-hosting. We only show benchmarks whose source allows republishing, and a list only from 10 models with a score and an active offer. Rank = position among the models of this catalogue with a score, not in the original list. Models for self-hosting by graphics card: [Self-hosting](https://models.searchit-agent.ai/en/self-hosting/) ## Knowledge - [MMLU-Pro (TIGER-Lab Leaderboard)](https://models.searchit-agent.ai/en/leaderboards/tiger-mmlu-pro/) – allgemein - Wissen ueber 14 Fachgebiete. ↑ 42 models · leader Gemini 3.1 Pro (Vorschau) (91.16 %) - [SimpleQA Verified (Epoch AI)](https://models.searchit-agent.ai/en/leaderboards/epoch-simpleqa/) – allgemein - Faktenwissen ohne Hilfsmittel, Halluzinationsneigung. ↑ 85 models · leader Gemini 4 Argon (76 %) ## Mathematics - [FrontierMath Tiers 1-3 v2 (Epoch AI)](https://models.searchit-agent.ai/en/leaderboards/epoch-frontiermath/) – allgemein - Mathematik bis Forschungsniveau. ↑ 91 models · leader GPT-6 astra (93.7 %) - [OTIS Mock AIME 2024-2025 (Epoch AI)](https://models.searchit-agent.ai/en/leaderboards/epoch-aime/) – allgemein - Wettbewerbsmathematik. ↑ 153 models · leader Claude Fable 5.1 (100 %) ## Coding - [SWE-bench Verified (Epoch AI)](https://models.searchit-agent.ai/en/leaderboards/epoch-swe/) – allgemein - Fehlerbehebung in echten Code-Repositories. ↑ 33 models · leader Opus 4.7 (83.5 %) ## Tool calling - [Berkeley Function-Calling Leaderboard V4](https://models.searchit-agent.ai/en/leaderboards/bfcl-v4/) – allgemein - Werkzeug- und Funktionsaufrufe, agentische Ablaeufe. ↑ 42 models · leader Opus 4.5 (77.47 %) ## Hallucination - [Vectara HHEM-2.3](https://models.searchit-agent.ai/en/leaderboards/hhem/) – Zusammenfassung - Treue zur Vorlage. ↓ 82 models · leader GPT-5.4 nano (3.1 %) ## Language tasks and extraction - [searchit Entity Extraction](https://models.searchit-agent.ai/en/leaderboards/searchit-entity-extraction/) – Extract details such as names, companies and amounts from German-language texts (measured by searchit).. ↑ 53 models · leader GPT-6 astra (77.1 %) _No leaderboard (scores on the model pages only): MÖVE (Bundesdruckerei), arXiv 2606.13111 (Licence of the source unclear); Structured Output Benchmark (SOB), arXiv 2604.25359 (Licence of the source unclear)._ ## General _No leaderboard (scores on the model pages only): LiveBench (Aufgabensatz 2026-01-08) (Licence of the source unclear)._ ## Image understanding _No leaderboard (scores on the model pages only): HallusionBench (llm-stats-Abzug) (Licence of the source unclear); MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69) (Licence of the source unclear); OCRBench v2, englische Spur (llm-stats-Abzug) (Licence of the source unclear)._ ## Embedding - [MTEB ArguAna](https://models.searchit-agent.ai/en/leaderboards/mteb-arguana/) – Retrieval (en). ↑ 38 models · leader gemini-embedding-001 (86.4) - [MTEB EnglishFinance1Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-englishfinance1retrieval/) – Retrieval (en). ↑ 34 models · leader Voyage 4 large (82.2) - [MTEB EnglishFinance2Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-englishfinance2retrieval/) – Retrieval (en). ↑ 34 models · leader Voyage 4 large (91) - [MTEB EnglishFinance3Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-englishfinance3retrieval/) – Retrieval (en). ↑ 34 models · leader gemini-embedding-001 (83.3) - [MTEB EnglishFinance4Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-englishfinance4retrieval/) – Retrieval (en). ↑ 34 models · leader Voyage 4 large (62) - [MTEB EnglishHealthcare1Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-englishhealthcare1retrieval/) – Retrieval (en). ↑ 32 models · leader Voyage 4 large (67.5) - [MTEB German1Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-german1retrieval/) – Retrieval (de). ↑ 35 models · leader gemini-embedding-001 (97.6) - [MTEB GermanDPR](https://models.searchit-agent.ai/en/leaderboards/mteb-germandpr/) – Retrieval (de). ↑ 22 models · leader most-embed-de (85.6) - [MTEB GermanHealthcare1Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-germanhealthcare1retrieval/) – Retrieval (de). ↑ 35 models · leader Voyage 4 large (91.4) - [MTEB GermanLegal1Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-germanlegal1retrieval/) – Retrieval (de). ↑ 35 models · leader Voyage 4 large (75.5) - [MTEB GermanQuAD-Retrieval](https://models.searchit-agent.ai/en/leaderboards/mteb-germanquad-retrieval/) – Retrieval (de). ↑ 26 models · leader most-embed-de (97.7) - [MTEB LegalQuAD](https://models.searchit-agent.ai/en/leaderboards/mteb-legalquad/) – Retrieval (de). ↑ 44 models · leader most-embed-de (76.2) - [MTEB NFCorpus](https://models.searchit-agent.ai/en/leaderboards/mteb-nfcorpus/) – Retrieval (en). ↑ 29 models · leader Qwen3 Embedding 8B (41.4) - [MTEB SciFact](https://models.searchit-agent.ai/en/leaderboards/mteb-scifact/) – Retrieval (en). ↑ 28 models · leader Qwen3 Embedding 8B (78.5) - [MTEB TRECCOVID](https://models.searchit-agent.ai/en/leaderboards/mteb-treccovid/) – Retrieval (en). ↑ 37 models · leader Qwen3 Embedding 8B (95) _No leaderboard (scores on the model pages only): Text zu Foto (Mittel ueber 3 Aufgaben) (too few models with an offer: 0, from 10); ViDoRe v1 (Mittel ueber 10 Aufgaben, Dokumentseite als Bild) (too few models with an offer: 0, from 10); ViDoRe v3 (Mittel ueber 9 Aufgaben) (too few models with an offer: 1, from 10)._ ## Other _No leaderboard (scores on the model pages only): ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction (arXiv:2607.29677) (Licence of the source unclear); LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) (Licence of the source unclear)._ --- Prices as of 7 Nov 2026. Providers' list prices, without guarantee.