# DeepSeek-V3.1 vs Mercury 2.5

> DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 6.3× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-mercury-2-5
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 23.3.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- Mercury 2.5 accepts more context: 260K tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 42.8 | 33.5 |
| Rank | 108 | 242 |
| Context | 164K | 260K |
| Input $/M | $0.25 | $0.04 |
| Output $/M | $0.95 | $0.15 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1: 40.3 (#144)
- Mercury 2.5: 39.5 (#156)

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| SciCode | — | 38.5% |
| WeirdML | 38.4% | — |
| LMArena Coding | 1417 | — |
| ALE-Bench | — | 301.65 |

## Reasoning

- DeepSeek-V3.1: 27.9 (#110)
- Mercury 2.5: 22.4 (#193)

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1417 | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 38.9 (#122)
- Mercury 2.5: 23.3 (#272)

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| ProofBench | — | 3% |
| LMArena Math | 1420 | — |

## Knowledge

- DeepSeek-V3.1: 43.7 (#90)
- Mercury 2.5: —

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |

## Multilingual

- DeepSeek-V3.1: 51.6 (#106)
- Mercury 2.5: —

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |

## Instruction Following

- DeepSeek-V3.1: 73.9 (#110)
- Mercury 2.5: —

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1400 | — |

## Long Context

- DeepSeek-V3.1: 36.3 (#232)
- Mercury 2.5: —

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| Fiction.LiveBench | 52.8% | — |
| LMArena Longer Query | 1422 | — |

## Writing & Preference

- DeepSeek-V3.1: 60.3 (#98)
- Mercury 2.5: —

| Benchmark | DeepSeek-V3.1 | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1436 | — |
| LMArena Multi-Turn | 1408 | — |

## FAQ

### Is DeepSeek-V3.1 better than Mercury 2.5?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 6.3× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.1 or Mercury 2.5?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

### Is DeepSeek-V3.1 or Mercury 2.5 better for coding?

They score almost the same on coding (40.3 vs 39.5); test both on your own repository before choosing.

### Which has the bigger context window?

Mercury 2.5 does, with 260K tokens against 164K.

### How many benchmarks do DeepSeek-V3.1 and Mercury 2.5 share?

0 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Mercury 2.5 has 4.