# Gemini 3.1 Pro Preview vs Llama 3.2 3B

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 28.9 on the Noometry Index. Llama 3.2 3B costs 38× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-llama-3-2-3b
- Last updated: 2026-10-12
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Llama 3.2 3B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 21.0.
- The biggest single-benchmark swing is BALROG: 57% for Gemini 3.1 Pro Preview and 10.1% for Llama 3.2 3B.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 131K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 56.7 | 28.9 |
| Rank | 23 | 321 |
| Context | 1.05M | 131K |
| Input $/M | $2 | $0.05 |
| Output $/M | $12 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.1 Pro Preview: 42.5 (#99)
- Llama 3.2 3B: 27.6 (#319)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1484 | 1098 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1447 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| BigCodeBench Instruct | — | 23.4% |
| MirrorCode | 8.9% | — |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#34)
- Llama 3.2 3B: 20.1 (#143)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| BALROG | 57% | 10.1% |
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| Berkeley Function Calling Leaderboard | — | 21.9% |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#12)
- Llama 3.2 3B: 21.0 (#228)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1095 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.77 | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.1 Pro Preview: 62.1 (#34)
- Llama 3.2 3B: 32.4 (#214)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1485 | 1126 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Llama 3.2 3B: 29.7 (#235)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1485 | 1090 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |

## Multimodal

- Gemini 3.1 Pro Preview: 37.9 (#69)
- Llama 3.2 3B: —

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.0 (#12)
- Llama 3.2 3B: 26.2 (#281)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1477 | 1019 |
| LMArena Chinese | 1529 | 1017 |
| LMArena German | 1491 | 1056 |
| LMArena Russian | 1498 | 949 |
| LMArena French | 1487 | — |
| LMArena Japanese | 1493 | — |
| LMArena Korean | 1455 | — |
| LMArena Spanish | 1479 | — |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.0 (#32)
- Llama 3.2 3B: 56.0 (#275)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1466 | 1089 |

## Long Context

- Gemini 3.1 Pro Preview: 47.4 (#18)
- Llama 3.2 3B: 33.4 (#261)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1483 | 1100 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.1 (#37)
- Llama 3.2 3B: 24.7 (#307)

| Benchmark | Gemini 3.1 Pro Preview | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1481 | 1110 |
| LMArena Creative Writing | 1482 | 1094 |
| EQ-Bench Creative Writing | 1491 | 595 |
| LMArena Multi-Turn | 1488 | 1105 |
| EQ-Bench 4 | 1142 | — |

## FAQ

### Is Gemini 3.1 Pro Preview better than Llama 3.2 3B?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 28.9 on the Noometry Index. Llama 3.2 3B costs 38× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.1 Pro Preview or Llama 3.2 3B?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or Llama 3.2 3B better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 3.1 Pro Preview and Llama 3.2 3B share?

15 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Llama 3.2 3B has 18.