# Deepseek Coder v2 vs Palm 2

> Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 30.0 on the Noometry Index.

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

## Summary

- They share 10 benchmarks with published results for both. Deepseek Coder v2 scores higher in 7 categories and Palm 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Deepseek Coder v2 leads 36.3 to 20.9.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.

## Snapshot

| | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 35.9 | 30.0 |
| Rank | 220 | 298 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Palm 2: 29.0 (#311)

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Coding | 1251 | 994 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Palm 2: 19.1 (#271)

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1005 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Palm 2: 30.8 (#231)

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Math | 1241 | 1049 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Palm 2: —

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Palm 2: 20.9 (#295)

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Non-English | 1182 | 916 |
| LMArena Chinese | 1201 | 887 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Palm 2: 51.0 (#296)

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1010 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Palm 2: 30.8 (#285)

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1219 | 1010 |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Palm 2: 25.6 (#304)

| Benchmark | Deepseek Coder v2 | Palm 2 |
|---|---|---|
| LMArena Text | 1191 | 1027 |
| LMArena Creative Writing | 1120 | 991 |
| LMArena Multi-Turn | 1177 | 994 |

## FAQ

### Is Deepseek Coder v2 better than Palm 2?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 30.0 on the Noometry Index.

### Is Deepseek Coder v2 or Palm 2 better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 29.0 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Palm 2 share?

10 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Palm 2 has 10.