Mercury 2.5
Public AI IQ model profile with source-backed benchmark results and derived ranking context.
Mercury 2.5 API pricing — full price table, workload cost examples, and cheaper alternatives.
Release and Capabilities
| Public release | 2026-09-08 |
|---|---|
| Modalities | text |
| Context window | 260,000 tokens |
Production access through Inception API, Baseten, and OpenRouter.
Publisher-reported capabilities
- Diffusion language model with tunable reasoning, parallel tool calls, and schema-aligned JSON.
- Supports a 260K-token context window.
Limitations and availability caveats
- The launch discount is temporary; stored pricing uses the published standard rate.
Official release and model references
Measured Coverage and Estimates
Mercury 2.5 has 14 of 39 tracked IQ benchmark inputs across 5 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. Configured predecessor references: Mercury 2. A reference is an estimation input, not evidence that this model has the predecessor's measured results.
Among dimensions with direct benchmark coverage, this profile's highest estimated scores are Reliability (IQ 110) and Academic Reasoning (IQ 108). 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 | 91 | 0/5 |
| Mathematical Reasoning | 96 | 1/5 |
| Academic Reasoning | 108 | 4/6 |
| Programmatic Reasoning | 100 | 2/6 |
| Computer Use | 96 | 0/5 |
| Reliability | 110 | 3/6 |
| Knowledge Work | 99 | 4/6 |
Benchmark Results
Compare
Frequently Asked Questions
- What is the IQ of Mercury 2.5?
- Mercury 2.5 has an estimated IQ of 100, which ranks #116 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 Mercury 2.5 cost?
- Mercury 2.5 costs $0.20 per million input tokens and $0.75 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.419 per million input-plus-output tokens.
- Is Mercury 2.5 open source?
- No — Mercury 2.5 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- When was Mercury 2.5 released?
- Mercury 2.5 was publicly released on September 8, 2026.
- How large is the context window of Mercury 2.5?
- Mercury 2.5 supports a context window of 260,000 tokens — the amount of text it can consider in a single request.
- How fast is Mercury 2.5?
- In independent measurements, Mercury 2.5 generates about 706 tokens per second, with a typical response time of about 4.1 seconds.