GPT-4.1 nano
OpenAIGPTProprietary
Description
GPT-4.1 nano is OpenAI's fastest and cheapest model available in the GPT-4.1 family. It delivers exceptional performance at a small size with its 1 million token context window. Ideal for tasks like classification or autocompletion.
Date de sortie
2025-04-14
Paramètres
—
Longueur du contexte
1.0M
Modalités
file, image, text
Radar de capacités
27
general
20
coding
36
reasoning
33
scienceest.
10
agents
85
multimodal
Science utilise un proxy de raisonnement lorsque les benchmarks scientifiques dédiés ne sont pas disponibles.
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Code Ranking | 341 | 20.0 | AA |
| General Ranking | 375 | 29.0 | AA |
| Math Reasoning | 242 | 36.0 | AA |
| Multimodal Ranking | 69 | 60.0 | LS |
| Reasoning | 102 | 17.0 | LS |
| Science | 329 | 33.0 | AA |
Scores de benchmarks (LLM Stats)
Biology
GPQA
50.3%Aut.
Code
Aider-Polyglot
9.8%Aut.
Aider-Polyglot Edit
6.2%Aut.
Communication
Multi-IF
57.2%Aut.
TAU-bench Retail
22.6%Aut.
Multi-Challenge
15.0%Aut.
TAU-bench Airline
14.0%Aut.
Finance
MMLU
80.1%Aut.
General
IFEval
74.5%Aut.
MMMLU
66.9%Aut.
MMMU
55.4%Aut.
Internal API instruction following (hard)
31.6%Aut.
Language
COLLIE
42.5%Aut.
Long Context
OpenAI-MRCR: 2 needle 128k
36.6%Aut.
OpenAI-MRCR: 2 needle 1M
12.0%Aut.
ComplexFuncBench
5.7%Aut.
Graphwalks parents >128k
5.6%Aut.
Graphwalks BFS >128k
2.9%Aut.
Math
MathVista
56.2%Aut.
AIME 2024
29.4%Aut.
Multimodal
CharXiv-D
73.9%Aut.
CharXiv-R
40.5%Aut.
Reasoning
Graphwalks BFS <128k
25.0%Aut.
Graphwalks parents <128k
9.4%Aut.
Indices d'évaluation AA
Math Index24.0
Intelligence Index13.0
Coding Index11.2
Math 5000.8
Mmlu Pro0.7
Gpqa0.5
Livecodebench0.3
Ifbench0.3
Scicode0.3
Aime 250.2
Aime0.2
Tau20.2
Lcr0.2
Hle0.0
Terminalbench Hard0.0
Scores par catégorie LLM Stats
Finance80
Legal80
Healthcare70
Instruction Following70
Vision60
Language60
Math60
Multimodal60
Structured Output50
Biology50
Chemistry50
General50
Physics50
Writing40
Communication30
Reasoning30
Spatial Reasoning10
Tool Calling10
Code10
Long Context10
Tarification
Prix d'entrée$0.1 / 1M tokens
Prix de sortie$0.4 / 1M tokens
Prix mixte (3:1)$0.175 / 1M tokens
Vitesse
Tokens/sec121.7 tokens/s
Délai du premier token0.52s
Temps de réponse0.52s
Fournisseurs disponibles
(Unités internes LS)| Fournisseur | Prix d'entrée | Prix de sortie |
|---|---|---|
| OpenAI | 100K | 400K |