o1-mini
Zero-eval
#1SuperGLUE
#2Cybersecurity CTFs
by OpenAI
+
+
+
+
About
o1-mini was created as a faster, more cost-effective reasoning model, designed to bring extended thinking capabilities to applications with tighter latency and budget constraints. Built to excel particularly in coding and STEM reasoning while maintaining affordability, it provides a more accessible entry point to reasoning-enhanced AI assistance.
+
+
+
+
Pricing Range
Input (per 1M)$3.00 -$3.30
Output (per 1M)$12.00 -$13.20
Providers2
+
+
+
+
Timeline
AnnouncedSep 12, 2024
ReleasedSep 12, 2024
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
6 benchmarks
Average Score
71.9%
Best Score
92.4%
High Performers (80%+)
3Performance Metrics
Max Context Window
193.5KAvg Throughput
107.5 tok/sAvg Latency
3ms+
+
+
+
All Benchmark Results for o1-mini
Complete list of benchmark scores with detailed information
| HumanEval | text | 0.92 | 92.4% | Self-reported | |
| MATH-500 | text | 0.90 | 90.0% | Self-reported | |
| MMLU | text | 0.85 | 85.2% | Self-reported | |
| SuperGLUE | text | 0.75 | 75.0% | Self-reported | |
| GPQA | text | 0.60 | 60.0% | Self-reported | |
| Cybersecurity CTFs | text | 0.29 | 28.7% | Self-reported |
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+