# DeepSeek V4 Flash vs Gemma 4 31B IT

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 1.7× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-gemma-4-31b-it
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 5 categories and Gemma 4 31B IT in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 26.4.
- The biggest single-benchmark swing is Chess Puzzles: 33% for DeepSeek V4 Flash and 5% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4 Flash.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 262K.

## Snapshot

| | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 53.6 | 43.2 |
| Rank | 32 | 85 |
| Context | 1M | 262K |
| Input $/M | $0.15 | $0.09 |
| Output $/M | $0.60 | $0.34 |
| Weights | Open | Open |

## Coding

- DeepSeek V4 Flash: 47.6 (#56)
- Gemma 4 31B IT: 41.9 (#98)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1581 | 1364 |
| SciCode | 49.9% | 43.4% |
| WeirdML | 63% | 52.3% |
| LMArena Coding | 1457 | 1459 |
| ALE-Bench | 1,306 | 925.5 |
| FrontierCode | 18.8% | — |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#25)
- Gemma 4 31B IT: 26.4 (#119)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 63.5% |
| NYT Connections (extended) | 89.6% | 70.6% |
| CritPt | 16.6% | 1.4% |
| Chess Puzzles | 33% | 5% |
| LMArena Hard Prompts | 1443 | 1448 |
| DTBench | 90.9% | 82.7% |
| LMCA | 41.7% | 39.3% |
| Epoch Capabilities Index | 154.51 | 142.74 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| ARC-AGI-1 | 89% | — |
| Thematic Generalization | — | 53% |
| Mystery Game Puzzles | 34% | — |
| Surface Evolver Bench | — | 30.6% |

## Math

- DeepSeek V4 Flash: 60.0 (#31)
- Gemma 4 31B IT: 41.3 (#72)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 73.3% |
| LMArena Math | 1427 | 1464 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |

## Knowledge

- DeepSeek V4 Flash: 55.5 (#43)
- Gemma 4 31B IT: 37.9 (#141)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 91% | 75.8% |
| SimpleQA Verified | 33.6% | 10.4% |
| LMArena Expert | 1441 | 1465 |
| Vectara Hallucination Rate | — | 7.4% |

## Multimodal

- DeepSeek V4 Flash: —
- Gemma 4 31B IT: 41.0 (#32)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1278 |
| LMArena Document | — | 1425 |

## Multilingual

- DeepSeek V4 Flash: 53.2 (#71)
- Gemma 4 31B IT: 54.0 (#52)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1420 | 1431 |
| LMArena Chinese | 1467 | 1478 |
| LMArena French | 1438 | 1436 |
| LMArena Russian | 1428 | 1462 |
| LMArena Spanish | 1437 | 1443 |
| LMArena German | 1418 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1383 | — |

## Instruction Following

- DeepSeek V4 Flash: 75.1 (#76)
- Gemma 4 31B IT: 75.6 (#58)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1421 | 1433 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#81)
- Gemma 4 31B IT: 44.2 (#67)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1435 | 1446 |

## Writing & Preference

- DeepSeek V4 Flash: 64.0 (#59)
- Gemma 4 31B IT: 60.7 (#92)

| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1432 | 1443 |
| LMArena Creative Writing | 1403 | 1416 |
| EQ-Bench Creative Writing | 1559 | 1368 |
| LMArena Multi-Turn | 1449 | 1452 |
| EQ-Bench 4 | — | 1120 |

## FAQ

### Is DeepSeek V4 Flash better than Gemma 4 31B IT?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 1.7× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek V4 Flash or Gemma 4 31B IT?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; DeepSeek V4 Flash lists at $0.15 and $0.60.

### Is DeepSeek V4 Flash or Gemma 4 31B IT better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 41.9 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4 Flash does, with 1M tokens against 262K.

### How many benchmarks do DeepSeek V4 Flash and Gemma 4 31B IT share?

29 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Gemma 4 31B IT has 35.