HumanEval+
Résultats des évaluations de l’IA et performances des modèles
Type: percentageReasoning
Résultats enregistrés
30
Score moyen
71.24%
Plage des scores
25% - 92.90%
Modèle en tête
92.90% - Phi 4 Reasoning
Scores au fil du temps
Scores individuels du benchmark tracés par date.
Résultats des modèles
| Organisation | Modèles | Date du résultat | Meilleur score | Informations | Déclaré par le fournisseur | Source |
|---|---|---|---|---|---|---|
| Phi 4 Reasoning | 30 avr. 2025 | 92,90 % | - | Oui | Source | |
| Phi 4 Reasoning Plus | 30 avr. 2025 | 92,30 % | - | Oui | Source | |
| Granite 3.0 8B Instruct | - | 86,09 % | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | Oui | Source | |
| Granite 3.1 8B Instruct | - | 86,09 % | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | Oui | Source | |
| Granite 3.2 8B Instruct | - | 86,09 % | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | Oui | Source | |
| Granite 3.2 8B Instruct Preview | - | 86,09 % | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4687; benches=14) | Oui | Source | |
| Granite 3.3 2B Instruct | 16 avr. 2025 | 86,09 % | inferred family alias from granite-3.3-8b-instruct (score=0.3627; benches=14) | Oui | Source | |
| Granite 3.3 8B Instruct | 16 avr. 2025 | 86,09 % | - | Oui | Source | |
| Granite Guardian 3.0 8B | - | 86,09 % | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | Oui | Source | |
| Granite Guardian 3.1 8B | - | 86,09 % | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | Oui | Source | |
| Granite Guardian 3.3 8B | - | 86,09 % | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | Oui | Source | |
| Granite Speech 3.2 8B | - | 86,09 % | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | Oui | Source | |
| Granite Speech 3.3 8B | - | 86,09 % | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | Oui | Source | |
| Granite 4.1 30B | 29 avr. 2026 | 85,37 % | pass@1 | Oui | Source | |
| Phi 1 | - | 82,80 % | inferred family alias from phi-4 (score=0.3100; benches=13) | Oui | Source | |
| Phi 2 | - | 82,80 % | inferred family alias from phi-4 (score=0.3100; benches=13) | Oui | Source | |
| Phi 4 | 12 déc. 2024 | 82,80 % | - | Oui | Source | |
| Granite 4.1 8B | 29 avr. 2026 | 79,88 % | pass@1 | Oui | Source | |
| Granite 4.0 Micro | 02 oct. 2025 | 78,30 % | inferred high-confidence family alias from granite-4.0-tiny-preview (score=0.4700; benches=12) | Oui | Source | |
| Granite 4.0 Small | 02 oct. 2025 | 78,30 % | inferred high-confidence family alias from granite-4.0-tiny-preview (score=0.4700; benches=12) | Oui | Source | |
| Granite 4.0 Tiny | 02 oct. 2025 | 78,30 % | inferred alias from granite-4.0-tiny-preview | Oui | Source | |
| Granite 4.0 Tiny Preview | 02 mai 2025 | 78,30 % | - | Oui | Source | |
| Granite 4.1 3B | 29 avr. 2026 | 76,83 % | pass@1 | Oui | Source | |
| Qwen 14B | - | 51,20 % | inferred family alias from qwen-2.5-14b-instruct (score=0.3060; benches=16) | Oui | Source | |
| Ernie 4.5 21B A3B | - | 25 % | inferred version-family alias from ernie-4.5 | Oui | Source |
