GPT-4.1
Multimodal
Zero-eval
#1Video-MME (long, no subtitles)
#1OpenAI-MRCR: 2 needle 1M
#1Graphwalks parents >128k
+5 more
by OpenAI
About
GPT-4.1 is a multimodal language model developed by OpenAI. The model shows competitive results across 30 benchmarks. It excels particularly in MMLU (90.2%), CharXiv-D (87.9%), IFEval (87.4%). With a 1.1M token context window, it can handle extensive documents and complex multi-turn conversations. The model is available through 1 API provider. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents OpenAI's latest advancement in AI technology.
Pricing Range
Input (per 1M)$2.00 -$2.00
Output (per 1M)$8.00 -$8.00
Providers1
Timeline
AnnouncedApr 14, 2025
ReleasedApr 14, 2025
Knowledge CutoffJun 1, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
30 benchmarks
Average Score
57.3%
Best Score
90.2%
High Performers (80%+)
4Performance Metrics
Max Context Window
1.1MAvg Throughput
100.0 tok/sAvg Latency
10msTop Categories
code
87.4%
vision
73.4%
math
72.2%
long_context
59.2%
agents
58.7%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
MMLU
Rank #8 of 78
#5Claude 3.5 Sonnet
90.4%
#6Claude 3.5 Sonnet
90.4%
#7DeepSeek-R1
90.8%
#8GPT-4.1
90.2%
#9Kimi K2 Instruct
89.5%
#10GPT-4o
88.7%
#11DeepSeek-V3
88.5%
CharXiv-D
Rank #3 of 5
#1GPT-4.1 mini
88.4%
#2GPT-4.5
90.0%
#3GPT-4.1
87.9%
#4GPT-4o
85.3%
#5GPT-4.1 nano
73.9%
IFEval
Rank #15 of 37
#12Llama 3.1 70B Instruct
87.5%
#13GPT-4.5
88.2%
#14Llama 3.1 405B Instruct
88.6%
#15GPT-4.1
87.4%
#16Kimi-k1.5
87.2%
#17Nova Micro
87.2%
#18DeepSeek-V3
86.1%
MMMLU
Rank #4 of 13
#1o1
87.7%
#2Claude Opus 4
88.8%
#3Claude Opus 4.1
98.4%
#4GPT-4.1
87.3%
#5Qwen3 235B A22B
86.7%
#6Claude Sonnet 4
86.5%
#7Claude 3.7 Sonnet
86.1%
MMMU
Rank #12 of 52
#9Claude 3.7 Sonnet
75.0%
#10GPT-4.5
75.2%
#11Gemini 2.0 Flash Thinking
75.4%
#12GPT-4.1
74.8%
#13Claude Sonnet 4
74.4%
#14Llama 4 Maverick
73.4%
#15Gemini 2.5 Flash-Lite
72.9%
All Benchmark Results for GPT-4.1
Complete list of benchmark scores with detailed information
MMLU MMLU benchmark | general | text | 0.90 | 90.2% | Self-reported |
CharXiv-D CharXiv-D benchmark | general | text | 0.88 | 87.9% | Self-reported |
IFEval IFEval benchmark | code | text | 0.87 | 87.4% | Self-reported |
MMMLU MMMLU benchmark | general | text | 0.87 | 87.3% | Self-reported |
MMMU MMMU benchmark | vision | multimodal | 0.75 | 74.8% | Self-reported |
MathVista MathVista benchmark | math | text | 0.72 | 72.2% | Self-reported |
Video-MME (long, no subtitles) Video-MME (long, no subtitles) benchmark | vision | video | 0.72 | 72.0% | Self-reported |
Multi-IF Multi-IF benchmark | general | text | 0.71 | 70.8% | Self-reported |
TAU-bench Retail TAU-bench Retail benchmark | agents | text | 0.68 | 68.0% | Self-reported |
GPQA GPQA benchmark | general | text | 0.66 | 66.3% | Self-reported |
Showing 1 to 10 of 30 benchmarks
Resources