New Release
Capabilities, modalities, and lifecycle fields pulled from the model database.
Comparative results across benchmarks shared by the selected models.
| LiveBench | 66.9% |
| Graphwalks bfs <128k | 62.3% |
| OpenAI-MRCR: 2 needle 128k | 56.4% |
| SimpleBench | 38.7% |
| Elimation Game | 439.6% |
| GPQA Diamond | 81.4% |
| Graphwalks parents <128k | 51.1% |
| Humanity's Last Exam | 17.7% |
| LisanBench | 33700.0% |
| LMArena Text | 139600.0% |
| LMArena WebDev | 110228.0% |
| ARC-AGI-1 | 21.3% |
| ARC-AGI-2 | 1.7% |
| BrowseComp Long Context 128k | 80.0% |
| EQ-Bench 3 | 129100.0% |
| FActScore hallucination rate | 38.7% |
| Thematic Generalisation | 180.0% |
| Confabulations | 1579.0% |
| VideoMME | 79.5% |
| Ai2 SciArena | 105385.0% |
| Aider-Polyglot | 72.0% |
| AIME 2024 | 93.4% |
| AIME 2025 | 92.7% |
| LongFact-Concepts hallucination rate | 3.0% |
| LongFact-Objects hallucination rate | 8.9% |
| NYT Connections | 68.8% |
Observed provider pricing per million tokens.
All unique meters observed across the selected models.
| Meter | o4 Mini |
|---|---|
| Input Text Tokens | $1.10 |
Providers that expose each model based on observed pricing data.
Plans that include each selected model, grouped by organisation.
2 plans
Maximum input and output token capacity.
Usage and distribution terms.
Model release chronology.
Most recent training data date (when available).
A deeper field-by-field view (including benchmarks, pricing, and links).
| General Information | |
| Context Window | Input: 200,000 Output: 100,000 |
| Modalities | In: Vision, Text Out: Text |
| Reasoning | - |
| Web access | - |
| Parameters | - |
| Training Tokens | - |
| License | Proprietary |
| Knowledge Cutoff | Jun 2024 |
| Status | Available |
| Release | Apr 2025 |
| Announced | Apr 2025 |
| Deprecation | - |
| Retirement | - |
| Links | |
| Operational Metrics | |
| Cost per 1M Tokens | Input: $1.10 Output: $4.40 |
| Latency | - |
| Throughput | - |
| Benchmarks | |
| AIME 2024 | |
| AIME 2025 | |
| ARC-AGI-1 | |
| ARC-AGI-2 | |
| Ai2 SciArena | |
| Aider-Polyglot | |
| BrowseComp Long Context 128k | |
| Confabulations | |
| EQ-Bench 3 | |
| Elimation Game | |
| FActScore hallucination rate | |
| GPQA Diamond | |
| Graphwalks bfs <128k | |
| Graphwalks parents <128k | |
| Humanity's Last Exam | |
| LMArena Text | |
| LMArena WebDev | |
| LisanBench | |
| LiveBench | |
| LongFact-Concepts hallucination rate | |
| LongFact-Objects hallucination rate | |
| NYT Connections | |
| OpenAI-MRCR: 2 needle 128k | |
| SimpleBench | |
| Thematic Generalisation | |
| VideoMME | |
