# Mercury 2 vs Ministral 8B

> Mercury 2 is the stronger model overall, scoring 38.8 to 27.8 on the Noometry Index. Ministral 8B costs 3.8× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mercury-2-vs-ministral-8b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Mercury 2 scores higher in 6 categories and Ministral 8B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 35.6 to 12.5.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Ministral 8B has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Ministral 8B |
|---|---|---|
| Provider | Inception | Mistral AI |
| Noometry Index | 38.8 | 27.8 |
| Rank | 167 | 321 |
| Context | 128K | 128K |
| Input $/M | $0.25 | $0.10 |
| Output $/M | $0.75 | $0.10 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.2 (#250)
- Ministral 8B: 34.4 (#226)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1391 | 1202 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |

## Agentic & Tool Use

- Mercury 2: —
- Ministral 8B: 16.2 (#140)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |

## Reasoning

- Mercury 2: 23.0 (#170)
- Ministral 8B: 17.7 (#279)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1191 |
| CritPt | 0.8% | — |
| DTBench | — | 45.7% |

## Math

- Mercury 2: —
- Ministral 8B: 23.7 (#262)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Math | — | 1188 |
| MATH Level 5 | — | 14.9% |

## Knowledge

- Mercury 2: 35.6 (#170)
- Ministral 8B: 12.5 (#292)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 7.4% |
| LMArena Expert | 1358 | 1170 |
| GPQA Diamond | — | 27.1% |

## Multilingual

- Mercury 2: 46.8 (#153)
- Ministral 8B: 35.3 (#242)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1331 | 1165 |
| LMArena Chinese | 1416 | 1193 |
| LMArena Russian | 1303 | 1195 |

## Instruction Following

- Mercury 2: 70.4 (#161)
- Ministral 8B: 60.7 (#245)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1328 | 1161 |

## Long Context

- Mercury 2: 40.4 (#149)
- Ministral 8B: 36.7 (#222)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1329 | 1212 |

## Writing & Preference

- Mercury 2: 54.0 (#151)
- Ministral 8B: 39.8 (#241)

| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Text | 1355 | 1191 |
| LMArena Creative Writing | 1289 | 1175 |
| LMArena Multi-Turn | 1358 | 1166 |

## FAQ

### Is Mercury 2 better than Ministral 8B?

Mercury 2 is the stronger model overall, scoring 38.8 to 27.8 on the Noometry Index. Ministral 8B costs 3.8× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

### Which is cheaper, Mercury 2 or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

### Is Mercury 2 or Ministral 8B better for coding?

Ministral 8B scores higher on coding benchmarks: 34.4 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Both accept 128K tokens.

### How many benchmarks do Mercury 2 and Ministral 8B share?

12 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Ministral 8B has 17.