# Mercury 2.5 vs Qwen3 32B

> Qwen3 32B is the stronger model overall, scoring 39.2 to 33.5 on the Noometry Index. Mercury 2.5 costs 18× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mercury-2-5-vs-qwen3-32b
- Last updated: 2026-10-12
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Mercury 2.5 scores higher in 2 categories and Qwen3 32B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 39.7 to 23.3.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- Mercury 2.5 accepts more context: 260K tokens versus 131K.
- Qwen3 32B has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 33.5 | 39.2 |
| Rank | 242 | 172 |
| Context | 260K | 131K |
| Input $/M | $0.04 | $0.70 |
| Output $/M | $0.15 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2.5: 39.5 (#156)
- Qwen3 32B: 37.7 (#190)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| SciCode | 38.5% | 35.4% |
| Aider Polyglot | — | 40% |
| LMArena Coding | — | 1358 |
| ALE-Bench | 301.65 | — |

## Agentic & Tool Use

- Mercury 2.5: —
- Qwen3 32B: 32.6 (#62)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- Mercury 2.5: 22.4 (#193)
- Qwen3 32B: 20.2 (#241)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| CritPt | 0% | 0.3% |
| Kagi LLM Benchmark | — | 54.9% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | — | 1334 |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |

## Math

- Mercury 2.5: 23.3 (#272)
- Qwen3 32B: 39.7 (#99)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| ProofBench | 3% | — |
| LMArena Math | — | 1399 |

## Knowledge

- Mercury 2.5: —
- Qwen3 32B: 40.0 (#125)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |

## Multilingual

- Mercury 2.5: —
- Qwen3 32B: 45.6 (#167)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |

## Instruction Following

- Mercury 2.5: —
- Qwen3 32B: 68.9 (#179)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | — | 1305 |

## Long Context

- Mercury 2.5: —
- Qwen3 32B: 43.8 (#87)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |

## Writing & Preference

- Mercury 2.5: —
- Qwen3 32B: 52.9 (#163)

| Benchmark | Mercury 2.5 | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |

## FAQ

### Is Mercury 2.5 better than Qwen3 32B?

Qwen3 32B is the stronger model overall, scoring 39.2 to 33.5 on the Noometry Index. Mercury 2.5 costs 18× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.

### Which is cheaper, Mercury 2.5 or Qwen3 32B?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

### Is Mercury 2.5 or Qwen3 32B better for coding?

Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 37.7 in the Noometry coding category.

### Which has the bigger context window?

Mercury 2.5 does, with 260K tokens against 131K.

### How many benchmarks do Mercury 2.5 and Qwen3 32B share?

2 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Qwen3 32B has 26.