# Mercury 2 vs Qwen3 32B

> Mercury 2 and Qwen3 32B score almost the same on the Noometry Index (39.1 vs 39.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mercury-2-vs-qwen3-32b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Mercury 2 scores higher in 4 categories and Qwen3 32B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3 32B leads 37.7 to 33.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12.3% for Mercury 2 and 5.9% for Qwen3 32B.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- Qwen3 32B accepts more context: 131K tokens versus 128K.
- Qwen3 32B has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Qwen3 32B |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 39.1 | 39.2 |
| Rank | 175 | 172 |
| Context | 128K | 131K |
| Input $/M | $0.25 | $0.70 |
| Output $/M | $0.75 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.5 (#255)
- Qwen3 32B: 37.7 (#190)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| SciCode | 38.7% | 35.4% |
| LMArena Coding | 1391 | 1358 |
| Aider Polyglot | — | 40% |
| LMArena WebDev | 1171 | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |

## Agentic & Tool Use

- Mercury 2: —
- Qwen3 32B: 32.6 (#62)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- Mercury 2: 23.8 (#170)
- Qwen3 32B: 20.2 (#241)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| CritPt | 0.8% | 0.3% |
| LMArena Hard Prompts | 1362 | 1334 |
| Kagi LLM Benchmark | — | 54.9% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |

## Math

- Mercury 2: —
- Qwen3 32B: 39.7 (#99)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LMArena Math | — | 1399 |

## Knowledge

- Mercury 2: 36.2 (#172)
- Qwen3 32B: 40.0 (#125)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 5.9% |
| LMArena Expert | 1358 | 1362 |
| GPQA Diamond | — | 65.7% |

## Multilingual

- Mercury 2: 46.6 (#157)
- Qwen3 32B: 45.6 (#167)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1331 | 1317 |
| LMArena Chinese | 1417 | 1357 |
| LMArena Russian | 1304 | 1311 |
| LMArena German | — | 1341 |

## Instruction Following

- Mercury 2: 70.2 (#165)
- Qwen3 32B: 68.9 (#179)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1305 |

## Long Context

- Mercury 2: 40.5 (#154)
- Qwen3 32B: 43.8 (#87)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1330 | 1327 |
| Fiction.LiveBench | — | 74.2% |

## Writing & Preference

- Mercury 2: 53.8 (#155)
- Qwen3 32B: 52.9 (#163)

| Benchmark | Mercury 2 | Qwen3 32B |
|---|---|---|
| LMArena Text | 1355 | 1340 |
| LMArena Creative Writing | 1289 | 1297 |
| LMArena Multi-Turn | 1358 | 1331 |

## FAQ

### Is Mercury 2 better than Qwen3 32B?

Mercury 2 and Qwen3 32B score almost the same on the Noometry Index (39.1 vs 39.2), so choose on price, context window or the category you care about most.

### Which is cheaper, Mercury 2 or Qwen3 32B?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

### Is Mercury 2 or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.7 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Qwen3 32B does, with 131K tokens against 128K.

### How many benchmarks do Mercury 2 and Qwen3 32B share?

14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3 32B has 26.