# DeepSeek LLM 67B vs Gemma 4 31B IT

> Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-gemma-4-31b-it
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemma 4 31B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 8.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 73.3% for Gemma 4 31B IT.

## Snapshot

| | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 24.8 | 43.2 |
| Rank | 341 | 85 |
| Context | — | 262K |
| Input $/M | — | $0.09 |
| Output $/M | — | $0.34 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- Gemma 4 31B IT: 41.9 (#98)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| LMArena Coding | 1096 | 1459 |
| LMArena WebDev | — | 1364 |
| SciCode | — | 43.4% |
| WeirdML | — | 52.3% |
| ALE-Bench | — | 925.5 |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- Gemma 4 31B IT: 26.4 (#119)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1070 | 1448 |
| Epoch Capabilities Index | 110.54 | 142.74 |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Thematic Generalization | — | 53% |
| DTBench | — | 82.7% |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- Gemma 4 31B IT: 41.3 (#72)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 73.3% |
| LMArena Math | 1108 | 1464 |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- Gemma 4 31B IT: 37.9 (#141)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 24.6% | 75.8% |
| SimpleQA Verified | — | 10.4% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1465 |

## Multimodal

- DeepSeek LLM 67B: —
- Gemma 4 31B IT: 41.0 (#32)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1278 |
| LMArena Document | — | 1425 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- Gemma 4 31B IT: 54.0 (#52)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1073 | 1431 |
| LMArena Chinese | 1132 | 1478 |
| LMArena French | — | 1436 |
| LMArena Russian | — | 1462 |
| LMArena Spanish | — | 1443 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- Gemma 4 31B IT: 75.6 (#58)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1079 | 1433 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- Gemma 4 31B IT: 44.2 (#67)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1092 | 1446 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- Gemma 4 31B IT: 60.7 (#92)

| Benchmark | DeepSeek LLM 67B | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1105 | 1443 |
| LMArena Creative Writing | 1067 | 1416 |
| LMArena Multi-Turn | 1082 | 1452 |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |

## FAQ

### Is DeepSeek LLM 67B better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Gemma 4 31B IT share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemma 4 31B IT has 35.