# Gemini 2.5 Flash vs Gemma 4 31B IT

> Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-gemma-4-31b-it
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Gemma 4 31B IT in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 4 31B IT leads 27.2 to 18.1.
- The biggest single-benchmark swing is LMCA: 27.5% for Gemini 2.5 Flash and 39.3% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 39.3 | 43.5 |
| Rank | 170 | 90 |
| Context | 1.05M | 262K |
| Input $/M | $0.30 | $0.09 |
| Output $/M | $2.50 | $0.34 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash: 35.8 (#220)
- Gemma 4 31B IT: 42.3 (#108)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| WeirdML | 41.9% | 52.3% |
| LMArena Coding | 1424 | 1459 |
| ALE-Bench | 661.88 | 925.5 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1366 |
| SciCode | — | 43.4% |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.8 (#74)
- Gemma 4 31B IT: —

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |

## Reasoning

- Gemini 2.5 Flash: 18.1 (#286)
- Gemma 4 31B IT: 27.2 (#122)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 63.5% |
| CritPt | 1.1% | 1.4% |
| LMArena Hard Prompts | 1422 | 1448 |
| DTBench | 76.5% | 82.7% |
| LMCA | 27.5% | 39.3% |
| Epoch Capabilities Index | 143.03 | 142.74 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| NYT Connections (extended) | — | 70.6% |
| ARC-AGI-1 | 33.3% | — |
| Chess Puzzles | — | 5% |
| EnigmaEval | 2.7% | — |
| Thematic Generalization | — | 53% |
| Surface Evolver Bench | — | 30.6% |
| ForecastBench | 60.6 | — |

## Math

- Gemini 2.5 Flash: 39.9 (#98)
- Gemma 4 31B IT: 43.2 (#81)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 73.3% |
| LMArena Math | 1415 | 1465 |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Flash: 36.4 (#168)
- Gemma 4 31B IT: 37.9 (#151)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 7.4% |
| LMArena Expert | 1426 | 1465 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 10.4% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |

## Multimodal

- Gemini 2.5 Flash: 41.8 (#32)
- Gemma 4 31B IT: 41.6 (#34)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1253 | 1277 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| LMArena Document | — | 1425 |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.3 (#88)
- Gemma 4 31B IT: 53.8 (#57)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1409 | 1431 |
| LMArena Chinese | 1450 | 1476 |
| LMArena French | 1433 | 1435 |
| LMArena Russian | 1415 | 1460 |
| LMArena Spanish | 1421 | 1444 |
| LMArena German | 1418 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1385 | — |

## Instruction Following

- Gemini 2.5 Flash: 75.7 (#54)
- Gemma 4 31B IT: 75.5 (#61)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1405 | 1433 |
| IFEval | 89.8% | — |

## Long Context

- Gemini 2.5 Flash: 47.5 (#17)
- Gemma 4 31B IT: 44.2 (#71)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1419 | 1446 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- Gemini 2.5 Flash: 53.8 (#157)
- Gemma 4 31B IT: 60.5 (#96)

| Benchmark | Gemini 2.5 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1417 | 1443 |
| LMArena Creative Writing | 1400 | 1415 |
| EQ-Bench Creative Writing | 1137 | 1368 |
| LMArena Multi-Turn | 1408 | 1452 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |
| EQ-Bench 4 | — | 1120 |

## FAQ

### Is Gemini 2.5 Flash better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.3 on the Noometry Index.

### Which is cheaper, Gemini 2.5 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; Gemini 2.5 Flash lists at $0.30 and $2.50.

### Is Gemini 2.5 Flash or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 35.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 262K.

### How many benchmarks do Gemini 2.5 Flash and Gemma 4 31B IT share?

25 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemma 4 31B IT has 35.