HumanEval+
AI बेंचमार्क के परिणाम और मॉडल का प्रदर्शन
प्रकार: percentageReasoning
दर्ज परिणाम
30
औसत स्कोर
71.24%
स्कोर सीमा
25% - 92.90%
अग्रणी मॉडल
92.90% - Phi 4 Reasoning
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 |
|---|---|---|---|---|---|---|
| Phi 4 Reasoning | 30 अप्रैल 2025 | 92.90% | - | हाँ | स्रोत | |
| Phi 4 Reasoning Plus | 30 अप्रैल 2025 | 92.30% | - | हाँ | स्रोत | |
| Granite 3.0 8B Instruct | - | 86.09% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | हाँ | स्रोत | |
| Granite 3.1 8B Instruct | - | 86.09% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | हाँ | स्रोत | |
| Granite 3.2 8B Instruct | - | 86.09% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | हाँ | स्रोत | |
| Granite 3.2 8B Instruct Preview | - | 86.09% | 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 | 86.09% | inferred family alias from granite-3.3-8b-instruct (score=0.3627; benches=14) | हाँ | स्रोत | |
| Granite 3.3 8B Instruct | 16 अप्रैल 2025 | 86.09% | - | हाँ | स्रोत | |
| Granite Guardian 3.0 8B | - | 86.09% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | हाँ | स्रोत | |
| Granite Guardian 3.1 8B | - | 86.09% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | हाँ | स्रोत | |
| Granite Guardian 3.3 8B | - | 86.09% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | हाँ | स्रोत | |
| Granite Speech 3.2 8B | - | 86.09% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | हाँ | स्रोत | |
| Granite Speech 3.3 8B | - | 86.09% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | हाँ | स्रोत | |
| Granite 4.1 30B | 29 अप्रैल 2026 | 85.37% | pass@1 | हाँ | स्रोत | |
| Phi 1 | - | 82.80% | inferred family alias from phi-4 (score=0.3100; benches=13) | हाँ | स्रोत | |
| Phi 2 | - | 82.80% | inferred family alias from phi-4 (score=0.3100; benches=13) | हाँ | स्रोत | |
| Phi 4 | 12 दिस॰ 2024 | 82.80% | - | हाँ | स्रोत | |
| Granite 4.1 8B | 29 अप्रैल 2026 | 79.88% | pass@1 | हाँ | स्रोत | |
| Granite 4.0 Micro | 02 अक्टू॰ 2025 | 78.30% | 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 | 78.30% | 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 | 78.30% | inferred alias from granite-4.0-tiny-preview | हाँ | स्रोत | |
| Granite 4.0 Tiny Preview | 02 मई 2025 | 78.30% | - | हाँ | स्रोत | |
| Granite 4.1 3B | 29 अप्रैल 2026 | 76.83% | pass@1 | हाँ | स्रोत | |
| Qwen 14B | - | 51.20% | inferred family alias from qwen-2.5-14b-instruct (score=0.3060; benches=16) | हाँ | स्रोत | |
| Ernie 4.5 21B A3B | - | 25% | inferred version-family alias from ernie-4.5 | हाँ | स्रोत |
