# Mercury 2 vs Qwen3.8 27B

> Qwen3.8 27B is the stronger model overall, scoring 46.0 to 39.1 on the Noometry Index. Mercury 2 costs 1.6× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mercury-2-vs-qwen3-8-27b
- Last updated: 2026-10-12
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Qwen3.8 27B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 23.8.
- The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 46.6% for Qwen3.8 27B.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.04 / $2.30 for Qwen3.8 27B.
- Qwen3.8 27B accepts more context: 262K tokens versus 128K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 39.1 | 46.0 |
| Rank | 175 | 68 |
| Context | 128K | 262K |
| Input $/M | $0.25 | $0.04 |
| Output $/M | $0.75 | $2.30 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.5 (#255)
- Qwen3.8 27B: 50.5 (#44)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | 1171 | 1593 |
| SciCode | 38.7% | 46.6% |
| LMArena Coding | 1391 | 1482 |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |

## Agentic & Tool Use

- Mercury 2: —
- Qwen3.8 27B: 32.9 (#57)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |

## Reasoning

- Mercury 2: 23.8 (#170)
- Qwen3.8 27B: 41.0 (#54)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| CritPt | 0.8% | 5.4% |
| LMArena Hard Prompts | 1362 | 1460 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |

## Math

- Mercury 2: —
- Qwen3.8 27B: 37.1 (#161)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1456 |

## Knowledge

- Mercury 2: 36.2 (#172)
- Qwen3.8 27B: 41.6 (#109)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1358 | 1482 |
| Vectara Hallucination Rate | 12.3% | — |

## Multimodal

- Mercury 2: —
- Qwen3.8 27B: 41.3 (#37)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |

## Multilingual

- Mercury 2: 46.6 (#157)
- Qwen3.8 27B: 53.7 (#60)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1331 | 1430 |
| LMArena Chinese | 1417 | 1504 |
| LMArena Russian | 1304 | 1415 |
| LMArena French | — | 1465 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1384 |
| LMArena Korean | — | 1393 |
| LMArena Spanish | — | 1448 |

## Instruction Following

- Mercury 2: 70.2 (#165)
- Qwen3.8 27B: 75.8 (#53)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1439 |

## Long Context

- Mercury 2: 40.5 (#154)
- Qwen3.8 27B: 44.3 (#70)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1330 | 1450 |

## Writing & Preference

- Mercury 2: 53.8 (#155)
- Qwen3.8 27B: 65.8 (#43)

| Benchmark | Mercury 2 | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1355 | 1441 |
| LMArena Creative Writing | 1289 | 1384 |
| LMArena Multi-Turn | 1358 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |

## FAQ

### Is Mercury 2 better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 39.1 on the Noometry Index. Mercury 2 costs 1.6× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.

### Which is cheaper, Mercury 2 or Qwen3.8 27B?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3.8 27B lists at $0.04 and $2.30.

### Is Mercury 2 or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 27B does, with 262K tokens against 128K.

### How many benchmarks do Mercury 2 and Qwen3.8 27B share?

14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3.8 27B has 31.