# Mercury 2 vs Qwen3 14B

> Mercury 2 is the stronger model overall, scoring 38.8 to 35.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-vs-qwen3-14b
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Mercury 2 scores higher in 2 categories and Qwen3 14B in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury 2 leads 23.0 to 18.1.
- The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 31.6% for Qwen3 14B.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
- Qwen3 14B accepts more context: 131K tokens versus 128K.
- Qwen3 14B has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Qwen3 14B |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 35.0 |
| Rank | 167 | 222 |
| Context | 128K | 131K |
| Input $/M | $0.25 | $0.35 |
| Output $/M | $0.75 | $1.40 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.2 (#250)
- Qwen3 14B: 36.7 (#191)

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| SciCode | 38.7% | 31.6% |
| LMArena WebDev | 1170 | — |
| WeirdML | 43.2% | — |
| LMArena Coding | 1391 | — |
| ALE-Bench | 785.58 | — |

## Agentic & Tool Use

- Mercury 2: —
- Qwen3 14B: 29.4 (#78)

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |

## Reasoning

- Mercury 2: 23.0 (#170)
- Qwen3 14B: 18.1 (#272)

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| CritPt | 0.8% | 0% |
| Kagi LLM Benchmark | — | 49.1% |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1362 | — |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
| Epoch Capabilities Index | — | 138.23 |

## Math

- Mercury 2: —
- Qwen3 14B: 37.0 (#102)

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |

## Knowledge

- Mercury 2: 35.6 (#170)
- Qwen3 14B: 39.2 (#124)

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 5.4% |
| GPQA Diamond | — | 63.8% |
| LMArena Expert | 1358 | — |

## Multilingual

- Mercury 2: 46.8 (#153)
- Qwen3 14B: —

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1331 | — |
| LMArena Chinese | 1416 | — |
| LMArena Russian | 1303 | — |

## Instruction Following

- Mercury 2: 70.4 (#161)
- Qwen3 14B: —

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| LMArena Instruction Following | 1328 | — |

## Long Context

- Mercury 2: 40.4 (#149)
- Qwen3 14B: 38.0 (#201)

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1329 | — |

## Writing & Preference

- Mercury 2: 54.0 (#151)
- Qwen3 14B: —

| Benchmark | Mercury 2 | Qwen3 14B |
|---|---|---|
| LMArena Text | 1355 | — |
| LMArena Creative Writing | 1289 | — |
| LMArena Multi-Turn | 1358 | — |

## FAQ

### Is Mercury 2 better than Qwen3 14B?

Mercury 2 is the stronger model overall, scoring 38.8 to 35.0 on the Noometry Index.

### Which is cheaper, Mercury 2 or Qwen3 14B?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.

### Is Mercury 2 or Qwen3 14B better for coding?

Qwen3 14B scores higher on coding benchmarks: 36.7 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen3 14B does, with 131K tokens against 128K.

### How many benchmarks do Mercury 2 and Qwen3 14B share?

3 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3 14B has 12.