Vibe-Eval
Ergebnisse von KI-Benchmarks und Modellleistung
Typ: percentageGeneral
Erfasste Ergebnisse
29
Durchschnittspunktzahl
58.09%
Punktzahlbereich
40.90% - 67.20%
Führendes Modell
67.20% - Gemini 2.5 Pro Preview TTS (2025-05-20)
Punktzahlen im Zeitverlauf
Einzelne Benchmark-Punktzahlen nach Datum.
Modellergebnisse
| Organisation | Modelle | Gemeldet am | Höchste Punktzahl | Info | Selbst gemeldet | Quelle |
|---|---|---|---|---|---|---|
| Gemini 2.5 Pro Preview TTS (2025-05-20) | 20. Mai 2025 | 67,20 % | inferred family alias from gemini-2.5-pro-preview-06-05 (score=0.4243; benches=13) | Ja | Quelle | |
| Gemini 2.5 Computer Use Preview | 07. Okt. 2025 | 65,60 % | inferred family alias from gemini-2.5-pro (score=0.3960; benches=16) | Ja | Quelle | |
| Gemini 2.5 Pro Experimental (2025-03-25) | 25. März 2025 | 65,60 % | inferred alias from gemini-2.5-pro | Ja | Quelle | |
| Gemini 2.5 Pro Preview TTS (2025-12-10) | 10. Dez. 2025 | 65,60 % | inferred modality/version alias from gemini-2.5-pro | Ja | Quelle | |
| Gemini Embedding 2 Preview | 10. März 2026 | 65,60 % | manual fallback alias from gemini-2.5-pro | Ja | Quelle | |
| Gemini 2.5 Flash Exp Native Audio Thinking Dialog | - | 65,40 % | inferred modality/version alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini 2.5 Flash Image (Nano Banana) | 02. Okt. 2025 | 65,40 % | inferred modality/version alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini 2.5 Flash Image Preview (Nano Banana) | 25. Aug. 2025 | 65,40 % | inferred modality/version alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini 2.5 Flash Native Audio Preview (2025-09-23) | - | 65,40 % | inferred modality/version alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini 2.5 Flash Preview (2025-09-25) | 25. Sept. 2025 | 65,40 % | inferred alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini 2.5 Flash Preview Native Audio Dialog | - | 65,40 % | inferred modality/version alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini 2.5 Flash Preview TTS (2025-05-20) | 20. Mai 2025 | 65,40 % | inferred modality/version alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini 2.5 Flash Preview TTS (2025-12-10) | 10. Dez. 2025 | 65,40 % | inferred modality/version alias from gemini-2.5-flash | Ja | Quelle | |
| Gemini Live 2.5 Flash Preview | 09. Apr. 2025 | 65,40 % | inferred high-confidence family alias from gemini-2.5-flash (score=0.5083; benches=14) | Ja | Quelle | |
| Gemini 2.0 Flash | 05. Feb. 2025 | 56,30 % | - | Ja | Quelle | |
| Gemini 2.0 Flash Exp | - | 56,30 % | inferred alias from gemini-2.0-flash | Ja | Quelle | |
| Gemini 2.0 Pro Exp (2025-02-05) | 05. Feb. 2025 | 56,30 % | inferred modality/version alias from gemini-2.0-flash | Ja | Quelle | |
| LearnLM 2.0 Flash Experimental | 17. Apr. 2025 | 56,30 % | inferred family alias from gemini-2.0-flash (score=0.3700; benches=13) | Ja | Quelle | |
| Gemini 1.5 Pro 001 | 23. Mai 2024 | 53,90 % | inferred alias from gemini-1.5-pro | Ja | Quelle | |
| Gemini 1.5 Pro Exp (2024-08-01) | 01. Aug. 2024 | 53,90 % | inferred alias from gemini-1.5-pro | Ja | Quelle | |
| Gemini 1.5 Pro Exp (2024-08-27) | 27. Aug. 2024 | 53,90 % | inferred alias from gemini-1.5-pro | Ja | Quelle | |
| Gemini Robotics ER 1.5 Preview | 25. Sept. 2025 | 53,90 % | inferred family alias from gemini-1.5-pro (score=0.3717; benches=23) | Ja | Quelle | |
| LearnLM 1.5 Pro Experimental | 19. Nov. 2024 | 53,90 % | inferred family alias from gemini-1.5-pro (score=0.3700; benches=23) | Ja | Quelle | |
| Gemini 2.5 Flash Lite Preview (2025-09-25) | 25. Sept. 2025 | 51,30 % | inferred alias from gemini-2.5-flash-lite | Ja | Quelle | |
| Gemini 1.5 Flash 001 | 23. Mai 2024 | 48,90 % | inferred alias from gemini-1.5-flash | Ja | Quelle |