# Mercury 2 vs Qwen-14B

> Mercury 2 is the stronger model overall, scoring 38.8 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Mercury 2 scores higher in 6 categories and Qwen-14B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 54.0 to 27.8.
- Qwen-14B has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Qwen-14B |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 30.8 |
| Rank | 167 | 273 |
| Context | 128K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.75 | — |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.2 (#250)
- Qwen-14B: 30.6 (#283)

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1391 | 1072 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |

## Reasoning

- Mercury 2: 23.0 (#170)
- Qwen-14B: 18.7 (#255)

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1027 |
| CritPt | 0.8% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 112.8 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |

## Math

- Mercury 2: —
- Qwen-14B: 28.7 (#224)

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |

## Knowledge

- Mercury 2: 35.6 (#170)
- Qwen-14B: —

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | — |
| LMArena Expert | 1358 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |

## Multilingual

- Mercury 2: 46.8 (#153)
- Qwen-14B: 27.7 (#270)

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1331 | 1042 |
| LMArena Chinese | 1416 | 1077 |
| LMArena Russian | 1303 | — |

## Instruction Following

- Mercury 2: 70.4 (#161)
- Qwen-14B: 52.6 (#284)

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1328 | 1031 |

## Long Context

- Mercury 2: 40.4 (#149)
- Qwen-14B: 31.3 (#276)

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1329 | 1029 |

## Writing & Preference

- Mercury 2: 54.0 (#151)
- Qwen-14B: 27.8 (#294)

| Benchmark | Mercury 2 | Qwen-14B |
|---|---|---|
| LMArena Text | 1355 | 1051 |
| LMArena Creative Writing | 1289 | 1028 |
| LMArena Multi-Turn | 1358 | 1022 |

## FAQ

### Is Mercury 2 better than Qwen-14B?

Mercury 2 is the stronger model overall, scoring 38.8 to 30.8 on the Noometry Index.

### Is Mercury 2 or Qwen-14B better for coding?

Mercury 2 scores higher on coding benchmarks: 33.2 versus 30.6 in the Noometry coding category.

### How many benchmarks do Mercury 2 and Qwen-14B share?

9 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen-14B has 18.