# Mercury 2 vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.4 to 38.8 on the Noometry Index. Mercury 2 costs 10× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mercury-2-vs-qwen3-7-max
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Qwen3.7 Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Max leads 61.7 to 35.6.
- The biggest single-benchmark swing is CritPt: 0.8% for Mercury 2 and 13.4% for Qwen3.7 Max.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 128K.

## Snapshot

| | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 51.4 |
| Rank | 167 | 35 |
| Context | 128K | 1M |
| Input $/M | $0.25 | $2.50 |
| Output $/M | $0.75 | $7.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Mercury 2: 33.2 (#250)
- Qwen3.7 Max: 50.2 (#43)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1170 | 1515 |
| SciCode | 38.7% | 48.8% |
| LMArena Coding | 1391 | 1498 |
| ALE-Bench | 785.58 | 1,189 |
| SWE-bench Verified | — | 77.3% |
| WeirdML | 43.2% | — |

## Agentic & Tool Use

- Mercury 2: —
- Qwen3.7 Max: 21.8 (#129)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |

## Reasoning

- Mercury 2: 23.0 (#170)
- Qwen3.7 Max: 48.4 (#36)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| CritPt | 0.8% | 13.4% |
| LMArena Hard Prompts | 1362 | 1483 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.74 |

## Math

- Mercury 2: —
- Qwen3.7 Max: 62.3 (#26)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| LMArena Math | — | 1488 |

## Knowledge

- Mercury 2: 35.6 (#170)
- Qwen3.7 Max: 61.7 (#24)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1358 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| Vectara Hallucination Rate | 12.3% | — |

## Multilingual

- Mercury 2: 46.8 (#153)
- Qwen3.7 Max: 57.1 (#13)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1331 | 1475 |
| LMArena Chinese | 1416 | 1533 |
| LMArena Russian | 1303 | 1482 |

## Instruction Following

- Mercury 2: 70.4 (#161)
- Qwen3.7 Max: 76.9 (#34)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1328 | 1460 |

## Long Context

- Mercury 2: 40.4 (#149)
- Qwen3.7 Max: 45.4 (#34)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1329 | 1484 |

## Writing & Preference

- Mercury 2: 54.0 (#151)
- Qwen3.7 Max: 65.2 (#52)

| Benchmark | Mercury 2 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1355 | 1476 |
| LMArena Creative Writing | 1289 | 1450 |
| LMArena Multi-Turn | 1358 | 1482 |
| EQ-Bench 4 | — | 1110 |

## FAQ

### Is Mercury 2 better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.4 to 38.8 on the Noometry Index. Mercury 2 costs 10× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

### Which is cheaper, Mercury 2 or Qwen3.7 Max?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

### Is Mercury 2 or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Max does, with 1M tokens against 128K.

### How many benchmarks do Mercury 2 and Qwen3.7 Max share?

15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3.7 Max has 33.