# Gemma 4 31B IT vs Nova Premier 1.0

> Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 37.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-nova-premier-1-0
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Gemma 4 31B IT scores higher in 5 categories and Nova Premier 1.0 in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 31.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 63.5% for Gemma 4 31B IT and 44.8% for Nova Premier 1.0.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| Provider | Google | Amazon |
| Noometry Index | 43.2 | 37.7 |
| Rank | 85 | 185 |
| Context | 262K | 1M |
| Input $/M | $0.09 | $2.50 |
| Output $/M | $0.34 | $12.50 |
| Weights | Open | Proprietary |

## Coding

- Gemma 4 31B IT: 41.9 (#98)
- Nova Premier 1.0: —

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| LMArena WebDev | 1364 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| LMArena Coding | 1459 | — |
| ALE-Bench | 925.5 | — |

## Reasoning

- Gemma 4 31B IT: 26.4 (#119)
- Nova Premier 1.0: 22.3 (#182)

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 44.8% |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| LMArena Hard Prompts | 1448 | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |

## Math

- Gemma 4 31B IT: 41.3 (#72)
- Nova Premier 1.0: 31.5 (#194)

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1464 | — |

## Knowledge

- Gemma 4 31B IT: 37.9 (#141)
- Nova Premier 1.0: 35.4 (#176)

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| MMLU-Pro | — | 72.6% |
| Vectara Hallucination Rate | 7.4% | — |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1465 | — |

## Multimodal

- Gemma 4 31B IT: 41.0 (#32)
- Nova Premier 1.0: —

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 54.0 (#52)
- Nova Premier 1.0: —

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1478 | — |
| LMArena French | 1436 | — |
| LMArena Russian | 1462 | — |
| LMArena Spanish | 1443 | — |

## Instruction Following

- Gemma 4 31B IT: 75.6 (#58)
- Nova Premier 1.0: 66.9 (#201)

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1433 | — |

## Long Context

- Gemma 4 31B IT: 44.2 (#67)
- Nova Premier 1.0: —

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1446 | — |

## Writing & Preference

- Gemma 4 31B IT: 60.7 (#92)
- Nova Premier 1.0: 51.0 (#174)

| Benchmark | Gemma 4 31B IT | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1416 | — |
| EQ-Bench Creative Writing | 1368 | — |
| WildBench | — | 78.8% |
| EQ-Bench 4 | 1120 | — |
| LMArena Multi-Turn | 1452 | — |

## FAQ

### Is Gemma 4 31B IT better than Nova Premier 1.0?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 37.7 on the Noometry Index.

### Which is cheaper, Gemma 4 31B IT or Nova Premier 1.0?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.

### Which has the bigger context window?

Nova Premier 1.0 does, with 1M tokens against 262K.

### How many benchmarks do Gemma 4 31B IT and Nova Premier 1.0 share?

1 benchmark has published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Nova Premier 1.0 has 6.