# DeepSeek-V2 (MoE-236B, May 2024) vs Mercury 2.5

> Mercury 2.5 has enough public results to be ranked (#242); 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-2-5
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2.5 |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 40.3 | 33.5 |
| Rank | — | 242 |
| Context | — | 260K |
| Input $/M | — | $0.04 |
| Output $/M | — | $0.15 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
- Mercury 2.5: 39.5 (#156)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2.5 |
|---|---|---|
| SciCode | — | 38.5% |
| BigCodeBench Instruct | 48.9% | — |
| BigCodeBench Complete | 59.4% | — |
| ALE-Bench | — | 301.65 |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2.5: 22.4 (#193)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2.5 |
|---|---|---|
| CritPt | — | 0% |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.77 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2.5: 23.3 (#272)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2.5 |
|---|---|---|
| ProofBench | — | 3% |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- Mercury 2.5: —

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mercury 2.5 |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than Mercury 2.5?

Mercury 2.5 has enough public results to be ranked (#242); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or Mercury 2.5 better for coding?

They score almost the same on coding (40.4 vs 39.5); test both on your own repository before choosing.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Mercury 2.5 share?

0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Mercury 2.5 has 4.