GPT-o1
OpenAILLMs
93.5
Performance
★ 4.6
Rating
520
Reviews
Text GenerationReasoningProprietary
About
OpenAI's reasoning model that uses extended chain-of-thought to solve complex math, science, and coding problems with higher accuracy.
Strengths
Designed for complex reasoning tasks. Achieved 83.3% on AIME 2024 (math competition) vs GPT-4o's 13.4%. State-of-the-art on GPQA Diamond (PhD-level science). Significantly better at multi-step logic, formal proofs, and algorithmic problems. Slower but much more accurate on hard tasks.
Specifications
- Context window
- 200,000
- Parameters
- —
Pricing
- Input cost
- $15.00 / 1M
- Output cost
- $60.00 / 1M
$15.00 input / $60.00 output per 1M tokens
Speed & Latency
- 20
- tokens/sec
- 2000ms
- time to first token
- 500 RPM (Tier 5)
- rate limits
Available On
OpenAI APIAzure OpenAIChatGPT Pro
Features
streamingvisionstructured outputreasoning tokens
Market Sentiment
Polymarket prediction market odds for "Best AI Model" — showing how the market values each provider over time.
Loading sentiment data...
Performance Trend
Benchmark score trends over time for the top 5 benchmarks.
Loading history...
Benchmarks
Scores from various benchmark tests; higher is better.
| Test | Score | Percentile | Source |
|---|---|---|---|
| BigBench Hard | 90.5 | p99 | seed |
| DROP | 90.2 | p99 | seed |
| GSM8K | 97.8 | p99 | seed |
| HumanEval | 92.4 |