# Mercury 2 vs Mixtral 8x22B

> Mercury 2 is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Mercury 2 scores higher in 7 categories and Mixtral 8x22B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 15.1.
- The biggest single-benchmark swing is WeirdML: 43.2% for Mercury 2 and 3.2% for Mixtral 8x22B.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Mercury 2 accepts more context: 128K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| Provider | Inception | Mistral AI |
| Noometry Index | 39.1 | 27.1 |
| Rank | 175 | 333 |
| Context | 128K | 64K |
| Input $/M | $0.25 | $2 |
| Output $/M | $0.75 | $6 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.5 (#255)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 43.2% | 3.2% |
| LMArena Coding | 1391 | 1166 |
| LMArena WebDev | 1171 | — |
| SciCode | 38.7% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 785.58 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- Mercury 2: —
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |

## Reasoning

- Mercury 2: 23.8 (#170)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1150 |
| CritPt | 0.8% | — |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |

## Math

- Mercury 2: —
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | — | 16.3% |
| LMArena Math | — | 1184 |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Mercury 2: 36.2 (#172)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1358 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 12.3% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- Mercury 2: 46.6 (#157)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1331 | 1128 |
| LMArena Chinese | 1417 | 1116 |
| LMArena Russian | 1304 | 1158 |
| LMArena French | — | 1166 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1057 |
| LMArena Spanish | — | 1151 |

## Instruction Following

- Mercury 2: 70.2 (#165)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- Mercury 2: 40.5 (#154)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1330 | 1144 |

## Writing & Preference

- Mercury 2: 53.8 (#155)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | Mercury 2 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1355 | 1162 |
| LMArena Creative Writing | 1289 | 1141 |
| LMArena Multi-Turn | 1358 | 1130 |
| WildBench | — | 71.1% |

## FAQ

### Is Mercury 2 better than Mixtral 8x22B?

Mercury 2 is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.

### Which is cheaper, Mercury 2 or Mixtral 8x22B?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is Mercury 2 or Mixtral 8x22B better for coding?

Mercury 2 scores higher on coding benchmarks: 33.5 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

Mercury 2 does, with 128K tokens against 64K.

### How many benchmarks do Mercury 2 and Mixtral 8x22B share?

12 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Mixtral 8x22B has 34.