# Grok Build 0.1 vs Mercury

> Mercury is the stronger model overall, scoring 37.3 to 35.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-build-0-1-vs-mercury
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Grok Build 0.1 leads 31.3 to 16.8.

## Snapshot

| | Grok Build 0.1 | Mercury |
|---|---|---|
| Provider | xAI | Inception |
| Noometry Index | 35.8 | 37.3 |
| Rank | 214 | 192 |
| Context | 256K | — |
| Input $/M | $1 | — |
| Output $/M | $2 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Grok Build 0.1: 42.5 (#90)
- Mercury: 38.1 (#164)

| Benchmark | Grok Build 0.1 | Mercury |
|---|---|---|
| SciCode | 50.2% | — |
| LMArena Coding | — | 1323 |

## Agentic & Tool Use

- Grok Build 0.1: 22.5 (#122)
- Mercury: —

| Benchmark | Grok Build 0.1 | Mercury |
|---|---|---|
| GBAEval | 2.4% | — |

## Reasoning

- Grok Build 0.1: 31.3 (#73)
- Mercury: 16.8 (#288)

| Benchmark | Grok Build 0.1 | Mercury |
|---|---|---|
| Kagi LLM Benchmark | — | 21.6% |
| CritPt | 9.1% | — |
| LMArena Hard Prompts | — | 1284 |

## Multilingual

- Grok Build 0.1: —
- Mercury: 41.7 (#201)

| Benchmark | Grok Build 0.1 | Mercury |
|---|---|---|
| LMArena Non-English | — | 1259 |

## Instruction Following

- Grok Build 0.1: —
- Mercury: 65.3 (#220)

| Benchmark | Grok Build 0.1 | Mercury |
|---|---|---|
| LMArena Instruction Following | — | 1238 |

## Long Context

- Grok Build 0.1: —
- Mercury: 38.3 (#193)

| Benchmark | Grok Build 0.1 | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1264 |

## Writing & Preference

- Grok Build 0.1: —
- Mercury: 46.2 (#216)

| Benchmark | Grok Build 0.1 | Mercury |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1186 |
| LMArena Multi-Turn | — | 1283 |

## FAQ

### Is Grok Build 0.1 better than Mercury?

Mercury is the stronger model overall, scoring 37.3 to 35.8 on the Noometry Index.

### Is Grok Build 0.1 or Mercury better for coding?

Grok Build 0.1 scores higher on coding benchmarks: 42.5 versus 38.1 in the Noometry coding category.

### How many benchmarks do Grok Build 0.1 and Mercury share?

0 benchmarks have published results for both models. Grok Build 0.1 has 3 scored results on Noometry and Mercury has 9.