# GPT-6.1 Sol vs Mercury 3

> Side-by-side benchmark comparison for GPT-6.1 Sol and Mercury 3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-6-1-sol-vs-mercury-3
- Last updated: October 19, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: GPT-6.1 Sol and Mercury 3 share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Mercury 3 has the lower published output-token price.
- GPT-6.1 Sol has the larger published context window at 1.05M.

## Model Snapshot

| Property | GPT-6.1 Sol | Mercury 3 |
|----------|----------|----------|
| Creator | OpenAI | Inception |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1.05M | 1M |
| Independent public score (not head-to-head) | 84.21 | null |
| Benchmarks Covered | 20 | 8 |
| Pricing (input/output) | $2.00 / $10.00 | $0.10 / $0.35 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GPT-6.1 Sol public-lane score: 76.2 (Estimated · #5/130)
- Mercury 3 public-lane score: Coming soon

| Benchmark | GPT-6.1 Sol | Mercury 3 | Winner |
|-----------|-----------|-----------|--------|
| AutomationBench | 36.1% | Coming soon | Coming soon |
| Terminal-Bench-Science 0.1 | 57.0% | Coming soon | Coming soon |
| ExploitGym | 35.1% | Coming soon | Coming soon |
| MazeBench | 17% | Coming soon | Coming soon |
| Hermes Index | 57.1% | Coming soon | Coming soon |
| Hermes Bench | 73.9% | Coming soon | Coming soon |
| τ³-bench results | Coming soon | 30.2% | Coming soon |
| BrowseComp+ | Coming soon | 55.18% | Coming soon |
| DeepSearchQA | Coming soon | 71.3% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GPT-6.1 Sol public-lane score: 71 (Supported · #8/151)
- Mercury 3 public-lane score: Coming soon

| Benchmark | GPT-6.1 Sol | Mercury 3 | Winner |
|-----------|-----------|-----------|--------|
| DeepSWE | 71.9% | 46.3% | GPT-6.1 Sol |
| Bug Hunt Bench | 44.3 fixes | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GPT-6.1 Sol public-lane score: 90.5 (#2/27)
- Mercury 3 public-lane score: Coming soon

| Benchmark | GPT-6.1 Sol | Mercury 3 | Winner |
|-----------|-----------|-----------|--------|
| STEMBench | 2.76 | Coming soon | Coming soon |
| ARC-AGI-1 | 96.50% | Coming soon | Coming soon |
| ARC-AGI-2 | 94.2% | Coming soon | Coming soon |
| ARC-AGI-3 | 52.7% | Coming soon | Coming soon |
| ARC-AGI-3 Provider Adapter | 96.18% | Coming soon | Coming soon |
| MRCRv2 | Coming soon | 75.5% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- GPT-6.1 Sol public-lane score: 87.3 (Unranked · 1 rankable row)
- Mercury 3 public-lane score: Coming soon

### Knowledge

- Winner: Insufficient shared evidence
- GPT-6.1 Sol public-lane score: 86.1 (Supported · #4/186)
- Mercury 3 public-lane score: Coming soon

| Benchmark | GPT-6.1 Sol | Mercury 3 | Winner |
|-----------|-----------|-----------|--------|
| HealthBench (raw) | 56.7% | Coming soon | Coming soon |
| HealthBench (length-adjusted) | 58.5% | Coming soon | Coming soon |
| HealthBench Professional | 64.2% | Coming soon | Coming soon |
| HealthBench Professional (raw) | 67.2% | Coming soon | Coming soon |
| HealthBench Hard | 36.2% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 89.2% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GPT-6.1 Sol public-lane score: Coming soon
- Mercury 3 public-lane score: Coming soon

| Benchmark | GPT-6.1 Sol | Mercury 3 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 76.8% | Coming soon |
| MultiChallenge (provider reports) | Coming soon | 60.35% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- GPT-6.1 Sol public-lane score: 97.3 (Unranked · 2 rankable rows)
- Mercury 3 public-lane score: Coming soon

| Benchmark | GPT-6.1 Sol | Mercury 3 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 93.684% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 100.000% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between GPT-6.1 Sol and Mercury 3?

Not yet. The models share only 1 sourced benchmark row, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [GPT-6.1 Sol vs GPT-6 Astra](/compare/gpt-6-1-sol-vs-gpt-6-astra)
- [Mercury 3 vs GPT-6 Astra](/compare/gpt-6-astra-vs-mercury-3)
- [GPT-6.1 Sol vs GPT-6 Sol](/compare/gpt-6-1-sol-vs-gpt-6-sol)
- [Mercury 3 vs GPT-6 Sol](/compare/gpt-6-sol-vs-mercury-3)

## Explore More

- [GPT-6.1 Sol profile](/models/gpt-6-1-sol)
- [Mercury 3 profile](/models/mercury-3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)