# Mercury 2 vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.1 to 38.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Mercury 2 scores higher in 1 category and Qwen2.5-Max in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5-Max leads 41.2 to 33.2.

## Snapshot

| | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 40.1 |
| Rank | 167 | 142 |
| Context | 128K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.75 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Mercury 2: 33.2 (#250)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1391 | 1359 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 785.58 | — |

## Reasoning

- Mercury 2: 23.0 (#170)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1360 |
| CritPt | 0.8% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.54 |
| LiveBench | — | 62.3% |

## Math

- Mercury 2: —
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | — | 58.4% |
| LMArena Math | — | 1369 |

## Knowledge

- Mercury 2: 35.6 (#170)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1358 | 1337 |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 12.3% | — |

## Multilingual

- Mercury 2: 46.8 (#153)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1331 | 1352 |
| LMArena Chinese | 1416 | 1382 |
| LMArena Russian | 1303 | 1353 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1299 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1377 |

## Instruction Following

- Mercury 2: 70.4 (#161)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1328 | 1335 |
| LiveBench Instruction Following | — | 75.3% |

## Long Context

- Mercury 2: 40.4 (#149)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1329 | 1358 |

## Writing & Preference

- Mercury 2: 54.0 (#151)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | Mercury 2 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1355 | 1367 |
| LMArena Creative Writing | 1289 | 1339 |
| LMArena Multi-Turn | 1358 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |

## FAQ

### Is Mercury 2 better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.1 to 38.8 on the Noometry Index.

### Is Mercury 2 or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 33.2 in the Noometry coding category.

### How many benchmarks do Mercury 2 and Qwen2.5-Max share?

11 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen2.5-Max has 27.