# Grok 4.1 Fast vs Mercury 2

> Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 38.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-1-fast-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Grok 4.1 Fast scores higher in 6 categories and Mercury 2 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 Fast leads 42.3 to 23.0.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 17.8% for Grok 4.1 Fast and 12.3% for Mercury 2.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.

## Snapshot

| | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| Provider | xAI | Inception |
| Noometry Index | 40.9 | 38.8 |
| Rank | 131 | 167 |
| Context | 128K | 128K |
| Input $/M | $0.20 | $0.25 |
| Output $/M | $0.50 | $0.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 4.1 Fast: 33.8 (#236)
- Mercury 2: 33.2 (#250)

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1241 | 1170 |
| LMArena Coding | 1411 | 1391 |
| ALE-Bench | 394.93 | 785.58 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |

## Agentic & Tool Use

- Grok 4.1 Fast: 36.1 (#35)
- Mercury 2: —

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 69.6% | — |
| τ²-bench Banking | 13.1% | — |
| LMArena Search | 1171 | — |
| Vending-Bench 2 | 1,107 | — |

## Reasoning

- Grok 4.1 Fast: 42.3 (#45)
- Mercury 2: 23.0 (#170)

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1407 | 1362 |
| SimpleBench | 56% | — |
| NYT Connections (extended) | 87.4% | — |
| CritPt | — | 0.8% |
| DTBench | 87.7% | — |
| ForecastBench | 61 | — |

## Math

- Grok 4.1 Fast: 30.9 (#201)
- Mercury 2: —

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| MathArena Final-Answer Competitions | 60.9% | — |
| ProofBench | 4% | — |
| LMArena Math | 1408 | — |

## Knowledge

- Grok 4.1 Fast: 32.6 (#203)
- Mercury 2: 35.6 (#170)

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 17.8% | 12.3% |
| LMArena Expert | 1398 | 1358 |

## Multimodal

- Grok 4.1 Fast: 36.3 (#71)
- Mercury 2: —

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| LMArena Vision | 1201 | — |

## Multilingual

- Grok 4.1 Fast: 51.1 (#110)
- Mercury 2: 46.8 (#153)

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1391 | 1331 |
| LMArena Chinese | 1441 | 1416 |
| LMArena Russian | 1387 | 1303 |
| LMArena French | 1416 | — |
| LMArena German | 1404 | — |
| LMArena Japanese | 1347 | — |
| LMArena Korean | 1361 | — |
| LMArena Spanish | 1411 | — |

## Instruction Following

- Grok 4.1 Fast: 72.8 (#127)
- Mercury 2: 70.4 (#161)

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1328 |

## Long Context

- Grok 4.1 Fast: 42.4 (#121)
- Mercury 2: 40.4 (#149)

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1390 | 1329 |

## Writing & Preference

- Grok 4.1 Fast: 57.4 (#126)
- Mercury 2: 54.0 (#151)

| Benchmark | Grok 4.1 Fast | Mercury 2 |
|---|---|---|
| LMArena Text | 1408 | 1355 |
| LMArena Creative Writing | 1394 | 1289 |
| LMArena Multi-Turn | 1389 | 1358 |
| EQ-Bench Creative Writing | 1327 | — |

## FAQ

### Is Grok 4.1 Fast better than Mercury 2?

Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 38.8 on the Noometry Index.

### Which is cheaper, Grok 4.1 Fast or Mercury 2?

Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

### Is Grok 4.1 Fast or Mercury 2 better for coding?

They score almost the same on coding (33.8 vs 33.2); test both on your own repository before choosing.

### Which has the bigger context window?

Both accept 128K tokens.

### How many benchmarks do Grok 4.1 Fast and Mercury 2 share?

14 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Mercury 2 has 17.