o1
Multimodal
by OpenAI
+
+
+
+
About
OpenAI o1, released by OpenAI in December 2024, is a reasoning-focused large language model that applies extended chain-of-thought processing before generating responses. It features a 200K token context window and native image understanding, demonstrating strong performance on STEM benchmarks requiring multi-step reasoning. o1 targets mathematics, science, and coding tasks where careful deliberation over the problem produces more accurate outputs than direct generation.
+
+
+
+
Pricing Range
Input (per 1M)$15.00 -$15.00
Output (per 1M)$60.00 -$60.00
Providers1
+
+
+
+
Timeline
ReleasedDec 5, 2024
Knowledge CutoffOct 1, 2023
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
2 benchmarks
Average Score
2.6%
Best Score
6.3%
High Performers (80%+)
0Performance Metrics
Max Context Window
300.0KTop Categories
Agents
6.3%
Multimodal
-1.0%
+
+
+
+
All Benchmark Results for o1
Complete list of benchmark scores with detailed information
| BrowseComp | Agents | 6.30 | 6.3% | Unverified | |
| MMMU | Multimodal | -1.00 | -1.0% | Unverified |