# Mercury 3 Benchmark Scores & Performance

> Mercury 3 by Inception has 8 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/mercury-3

Last updated: October 19, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Inception |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 1M |
| Official model card | [Inception Mercury 3 launch post](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Mercury 3
- Variant: base
- Benchmarks covered: 8 of 644
- Related earlier model: [Mercury 2.5](/models/mercury-2-5)
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [τ³-bench results](/benchmarks/tau3-bench) | 30.2% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |
| [BrowseComp+](/benchmarks/browsecomp-plus) | 55.18% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |
| [DeepSearchQA](/benchmarks/deepsearchqa) | 71.3% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [DeepSWE](/benchmarks/deepswe) | 46.3% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MRCRv2](/benchmarks/mrcrv2) | 75.5% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA-D](/benchmarks/gpqa-diamond) | 89.2% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFBench](/benchmarks/ifbench) | 76.8% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |
| [MultiChallenge (provider reports)](/benchmarks/multichallenge-provider-reports) | 60.35% | [Inception: Mercury 3 medium-reasoning launch chart](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |

## Other Inception Models

- [Mercury 2.5](/models/mercury-2-5) - Score: 33.98
- [Mercury 2](/models/mercury-2) - Score: 33.73
- [Mercury Voice](/models/mercury-voice) - Score: not computed
- [Mercury 2.5 Preview](/models/mercury-2-5-preview) - Score: not computed
- [Mercury Edit 2](/models/mercury-edit-2) - Score: not computed