BIG-Bench Hard
AI बेंचमार्क के परिणाम और मॉडल का प्रदर्शन
प्रकार: percentageLanguage
दर्ज परिणाम
28
औसत स्कोर
70.89%
स्कोर सीमा
44.30% - 89.20%
अग्रणी मॉडल
89.20% - Gemini 1.5 Pro 001
समय के साथ स्कोर
तारीख के अनुसार दिखाए गए अलग-अलग बेंचमार्क स्कोर।
मॉडल परिणाम
| संगठन | मॉडल | रिपोर्ट किया गया | सबसे ऊँचा स्कोर | जानकारी | स्व-रिपोर्ट किया गया | स्रोत |
|---|---|---|---|---|---|---|
| Gemini 1.5 Pro 001 | 23 मई 2024 | 89.20% | inferred alias from gemini-1.5-pro | हाँ | स्रोत | |
| Gemini 1.5 Pro Exp (2024-08-01) | 01 अग॰ 2024 | 89.20% | inferred alias from gemini-1.5-pro | हाँ | स्रोत | |
| Gemini 1.5 Pro Exp (2024-08-27) | 27 अग॰ 2024 | 89.20% | inferred alias from gemini-1.5-pro | हाँ | स्रोत | |
| Gemini Robotics ER 1.5 Preview | 25 सित॰ 2025 | 89.20% | inferred family alias from gemini-1.5-pro (score=0.3717; benches=23) | हाँ | स्रोत | |
| LearnLM 1.5 Pro Experimental | 19 नव॰ 2024 | 89.20% | inferred family alias from gemini-1.5-pro (score=0.3700; benches=23) | हाँ | स्रोत | |
| Gemini 1.5 Flash 001 | 23 मई 2024 | 85.50% | inferred alias from gemini-1.5-flash | हाँ | स्रोत | |
| Gemini 1.5 Flash Preview | 14 मई 2024 | 85.50% | inferred alias from gemini-1.5-flash | हाँ | स्रोत | |
| Phi 3.5 MoE instruct | 23 अग॰ 2024 | 79.10% | - | हाँ | स्रोत | |
| Phi 4 Mini | 01 फ़र॰ 2025 | 70.40% | - | हाँ | स्रोत | |
| Granite 3.0 8B Instruct | - | 69.13% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | हाँ | स्रोत | |
| Granite 3.1 8B Instruct | - | 69.13% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | हाँ | स्रोत | |
| Granite 3.2 8B Instruct | - | 69.13% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | हाँ | स्रोत | |
| Granite 3.2 8B Instruct Preview | - | 69.13% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4687; benches=14) | हाँ | स्रोत | |
| Granite 3.3 2B Instruct | 16 अप्रैल 2025 | 69.13% | inferred family alias from granite-3.3-8b-instruct (score=0.3627; benches=14) | हाँ | स्रोत | |
| Granite 3.3 8B Instruct | 16 अप्रैल 2025 | 69.13% | - | हाँ | स्रोत | |
| Granite Guardian 3.0 8B | - | 69.13% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | हाँ | स्रोत | |
| Granite Guardian 3.1 8B | - | 69.13% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | हाँ | स्रोत | |
| Granite Guardian 3.3 8B | - | 69.13% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | हाँ | स्रोत | |
| Granite Speech 3.2 8B | - | 69.13% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | हाँ | स्रोत | |
| Granite Speech 3.3 8B | - | 69.13% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | हाँ | स्रोत | |
| Phi 3 Mini 128K Instruct | - | 69% | inferred family alias from phi-3.5-mini-instruct (score=0.3533; benches=31) | हाँ | स्रोत | |
| Phi 3.5 mini instruct | 23 अग॰ 2024 | 69% | - | हाँ | स्रोत | |
| Granite 4.0 Micro | 02 अक्टू॰ 2025 | 55.70% | inferred high-confidence family alias from granite-4.0-tiny-preview (score=0.4700; benches=12) | हाँ | स्रोत | |
| Granite 4.0 Small | 02 अक्टू॰ 2025 | 55.70% | inferred high-confidence family alias from granite-4.0-tiny-preview (score=0.4700; benches=12) | हाँ | स्रोत | |
| Granite 4.0 Tiny | 02 अक्टू॰ 2025 | 55.70% | inferred alias from granite-4.0-tiny-preview | हाँ | स्रोत |
