# DeepSeek-V2 (MoE-236B, May 2024) vs Mercury 2

> Mercury 2 has enough public results to be ranked (#167); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-v2-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 33.2.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 39.7 | 38.8 |
| Rank | — | 167 |
| Context | — | 128K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.75 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
- Mercury 2: 33.2 (#250)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| LMArena WebDev | — | 1170 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1391 |
| BigCodeBench Complete | 59.4% | — |
| ALE-Bench | — | 785.58 |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2: 23.0 (#170)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| CritPt | — | 0.8% |
| LMArena Hard Prompts | — | 1362 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2: 35.6 (#170)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2: 46.8 (#153)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| LMArena Non-English | — | 1331 |
| LMArena Chinese | — | 1416 |
| LMArena Russian | — | 1303 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2: 70.4 (#161)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2: 40.4 (#149)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1329 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2: 54.0 (#151)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2 |
|---|---|---|
| LMArena Text | — | 1355 |
| LMArena Creative Writing | — | 1289 |
| LMArena Multi-Turn | — | 1358 |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than Mercury 2?

Mercury 2 has enough public results to be ranked (#167); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or Mercury 2 better for coding?

DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 33.2 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Mercury 2 share?

0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Mercury 2 has 17.