Agnes 2.5 Pro Beta
Public AI IQ model profile with source-backed benchmark results and derived ranking context.
Agnes 2.5 Pro Beta API pricing — full price table, workload cost examples, and cheaper alternatives.
Release and Capabilities
| Public release | 2026-08-26 |
|---|---|
| Modalities | text, image |
| Context window | 1,000,000 tokens |
Available through the Agnes AI API as the Beta checkpoint of Agnes 2.5 Pro
Publisher-reported capabilities
- Agnes 2.5 Pro Beta is a proprietary multimodal reasoning model with a 1M-token context window.
- Artificial Analysis measured a 49 Intelligence Index score, with the largest gains over Alpha in agentic tasks.
Limitations and availability caveats
- The model is explicitly labeled Beta and may change before the final Agnes 2.5 Pro release.
- Agnes AI has not disclosed the model's parameter count or released downloadable Beta weights.
Official release and model references
Measured Coverage and Estimates
Agnes 2.5 Pro Beta has 7 of 39 tracked IQ benchmark inputs across 2 of 7 dimensions. Raw benchmark tables contain source-backed results only. Derived IQ combines all six dimensions using the shared scoring methodology, including estimates where direct coverage is incomplete.
Among dimensions with direct benchmark coverage, this profile's highest estimated scores are Academic Reasoning (IQ 127) and Reliability (IQ 116). These dimension estimates can include statistical adjustments or predecessor priors; they are not raw benchmark percentages or claims of real-world task success.
Benchmark versions, evaluation harnesses, and coverage affect comparisons; a missing result is not a score of zero. See the scoring methodology for estimation and uncertainty limits.
IQ Dimensions
| Dimension | IQ | Coverage |
|---|---|---|
| Abstract Reasoning | 97 | 0/5 |
| Mathematical Reasoning | 104 | 0/5 |
| Academic Reasoning | 127 | 5/6 |
| Programmatic Reasoning | 98 | 0/6 |
| Computer Use | 109 | 0/5 |
| Reliability | 116 | 2/6 |
| Knowledge Work | 104 | 0/6 |
Benchmark Results
| Benchmark | Score | Dimension |
|---|---|---|
| AA Long Context Reasoning v1.1 | 83 | Reliability |
| AA Omniscience | -10.5333 | Reliability |
| CritPt | 15.7143 | Academic Reasoning |
| GPQA Diamond | 90.5051 | Academic Reasoning |
| Humanity's Last Exam | 37.5348 | Academic Reasoning |
| MMMU-Pro | 75.4335 | Academic Reasoning |
| SciCode | 48.8426 | Academic Reasoning |
Compare
Frequently Asked Questions
- What is the IQ of Agnes 2.5 Pro Beta?
- Agnes 2.5 Pro Beta has an estimated IQ of 108, which ranks #79 out of 164 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
- How much does Agnes 2.5 Pro Beta cost?
- Agnes 2.5 Pro Beta costs $0.10 per million input tokens and $0.30 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.5374 per million input-plus-output tokens.
- Is Agnes 2.5 Pro Beta open source?
- No — Agnes 2.5 Pro Beta is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- When was Agnes 2.5 Pro Beta released?
- Agnes 2.5 Pro Beta was publicly released on August 26, 2026.
- How large is the context window of Agnes 2.5 Pro Beta?
- Agnes 2.5 Pro Beta supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
- How fast is Agnes 2.5 Pro Beta?
- In independent measurements, Agnes 2.5 Pro Beta generates about 159 tokens per second, with a typical response time of about 18 seconds.