# DeepSeek LLM 67B vs Mercury 2

> Mercury 2 is the stronger model overall, scoring 39.1 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-mercury-2
- Last updated: 2026-10-12
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 24.9 | 39.1 |
| Rank | 347 | 175 |
| Context | — | 128K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.75 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Mercury 2: 33.5 (#255)

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| LMArena Coding | 1096 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Mercury 2: 23.8 (#170)

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1362 |
| CritPt | — | 0.8% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Mercury 2: —

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Mercury 2: 36.2 (#172)

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Mercury 2: 46.6 (#157)

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1073 | 1331 |
| LMArena Chinese | 1132 | 1417 |
| LMArena Russian | — | 1304 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Mercury 2: 70.2 (#165)

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1329 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Mercury 2: 40.5 (#154)

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1092 | 1330 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Mercury 2: 53.8 (#155)

| Benchmark | DeepSeek LLM 67B | Mercury 2 |
|---|---|---|
| LMArena Text | 1105 | 1355 |
| LMArena Creative Writing | 1067 | 1289 |
| LMArena Multi-Turn | 1082 | 1358 |

## FAQ

### Is DeepSeek LLM 67B better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 39.1 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Mercury 2 better for coding?

Mercury 2 scores higher on coding benchmarks: 33.5 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Mercury 2 share?

9 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mercury 2 has 17.