# Mercury 3

Inception · Proprietary · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/models/mercury-3  
JSON: https://modelscale.dev/api/model/mercury-3

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `mercury-3` | — |
| Overall score | Unavailable | Unavailable · source benchlm:models |
| Context window | 1M tokens | Observed 2026-10-23 · source benchlm:models |
| Release date | 2026-10-19 | Observed 2026-10-23 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $0.16 | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero.

| Axis | Score | Evidence |
| --- | --- | --- |
| Agentic | Unavailable | Unavailable · source benchlm:models |
| Coding | Unavailable | Unavailable · source benchlm:models |
| Knowledge | Unavailable | Unavailable · source benchlm:models |
| Reasoning | Unavailable | Unavailable · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |
| Throughput | 246 tok/s | 2026-10-23 | 2026-10-23 | Observed 2026-10-23 · source openrouter:endpoints |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $0.10 | Observed 2026-10-23 · source benchlm:pricing |
| Output / 1M tokens | $0.35 | Observed 2026-10-23 · source benchlm:pricing |
| Cache read / 1M tokens | $0.01 | Observed 2026-10-23 · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $0.16 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Fetch failed · source livebench:table |

**Self-hosted listing.** Inception lists a 50% launch offer at $0.10/M input, $0.01/M cached input, and $0.35/M output. Standard rates are $0.20/M input, $0.02/M cached input, and $0.70/M output. No promotion end date is stated as of October 19, 2026. The rates above are a hosted price matched from another provider, not a first-party list price.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $0.46 |
| Modelled tokens | 2.82M |

## Benchmark record

8 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA-D (GPQA Diamond) | 89.2 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| DeepSWE | 46.3 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| MRCRv2 | 75.5 | Long-context retrieval | Hard long-context | [Introducing GPT-5.2 and GPT-5.2 Pro](https://openai.com/index/introducing-gpt-5-2/) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| IFBench (Instruction Following Benchmark) | 76.84 | — | — | [BenchLM](https://benchlm.ai/benchmarks/ifbench) |
| MultiChallenge (provider reports) (MultiChallenge: provider-reported runs) | 60.35 | — | — | [MultiChallenge](https://labs.scale.com/leaderboard/multichallenge) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| DeepSearchQA | 71.3 | Agentic browsing and list-answer questions | Agentic web research | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |
| τ³-bench results (τ³-Bench Tool-Agent-User Evaluation) | 30.2 | Corrected customer-service tasks plus knowledge and voice evaluation modes | Long-horizon, multimodal, and knowledge-aware tool use | [Official τ³-bench repository and release notes](https://github.com/sierra-research/tau2-bench) |
| BrowseComp+ (BrowseComp-Plus) | 55.18 | — | — | [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://arxiv.org/abs/2508.06600) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-10-23 13:17 UTC.