New Release
Capabilities, modalities, and lifecycle fields pulled from the model database.
Comparative results across benchmarks shared by the selected models.
| CharXiv-Reasoning | 75.5% |
| ARC-AGI-1 | 5.3% |
| ARC-AGI-2 | 0.8% |
| OpenAI-MRCR: 2 needle 128k | 84.3% |
| OpenAI-MRCR: 2 needle 256k | 58.8% |
| Graphwalks parents <128k | 64.3% |
| HMMT 2025 | 87.8% |
| Humanity's Last Exam | 16.7% |
| MMMU Pro | 74.1% |
| COLLIE | 98.5% |
| MMMU | 81.6% |
| MMLU Pro | 62.3% |
| BrowseComp Long Context 128k | 89.4% |
| BrowseComp Long Context 256k | 86.0% |
| Tau 2 Airline | 60.0% |
| Confabulations | 1328.0% |
| Creative Story Writing | 831.0% |
| ERQA | 62.9% |
| FActScore hallucination rate | 3.5% |
| Frontier Math | 22.1% |
| GPQA Diamond | 82.3% |
| Graphwalks bfs <128k | 73.4% |
| LongFact-Objects hallucination rate | 1.3% |
| MathArena Apex | 1.0% |
| Tau 2 Retail | 78.3% |
| Tau 2 Telecom | 74.1% |
| VideoMME | 78.5% |
| LongFact-Concepts hallucination rate | 0.7% |
| SWE-Bench | 71.0% |
| Video MMMU | 82.5% |
| Aider-Polyglot | 71.6% |
| AIME 2025 | 91.1% |
Observed provider pricing per million tokens.
All unique meters observed across the selected models.
| Meter | GPT 5 Mini |
|---|---|
| Input Text Tokens | $0.25 |
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: 400,000 Output: 128,000 |
| Modalities | In: Text, Vision Out: Text |
| Reasoning | - |
| Web access | - |
| Parameters | - |
| Training Tokens | - |
| License | Proprietary |
| Knowledge Cutoff | May 2024 |
| Status | Available |
| Release | Aug 2025 |
| Announced | Aug 2025 |
| Deprecation | - |
| Retirement | - |
| Links | |
| Operational Metrics | |
| Cost per 1M Tokens | Input: $0.25 Output: $2.00 |
| Latency | - |
| Throughput | - |
| Benchmarks | |
| AIME 2025 | |
| ARC-AGI-1 | |
| ARC-AGI-2 | |
| Aider-Polyglot | |
| BrowseComp Long Context 128k | |
| BrowseComp Long Context 256k | |
| COLLIE | |
| CharXiv-Reasoning | |
| Confabulations | |
| Creative Story Writing | |
| ERQA | |
| FActScore hallucination rate | |
| Frontier Math | |
| GPQA Diamond | |
| Graphwalks bfs <128k | |
| Graphwalks parents <128k | |
| HMMT 2025 | |
| Humanity's Last Exam | |
| LongFact-Concepts hallucination rate | |
| LongFact-Objects hallucination rate | |
| MMLU Pro | |
| MMMU | |
| MMMU Pro | |
| MathArena Apex | |
| OpenAI-MRCR: 2 needle 128k | |
| OpenAI-MRCR: 2 needle 256k | |
| SWE-Bench | |
| Tau 2 Airline | |
| Tau 2 Retail | |
| Tau 2 Telecom | |
| Video MMMU | |
| VideoMME | |
