# Gemini 3.1 Pro Preview vs Llama-3.3-70B-Instruct

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 29× 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-3-3-70b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Llama-3.3-70B-Instruct 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 14.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro Preview and 5.1% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 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 128K.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 56.7 | 30.6 |
| Rank | 23 | 291 |
| Context | 1.05M | 128K |
| Input $/M | $2 | $0.10 |
| Output $/M | $12 | $0.32 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.1 Pro Preview: 42.5 (#99)
- Llama-3.3-70B-Instruct: 31.0 (#290)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| SciCode | 58.9% | 26% |
| WeirdML | 72.1% | 14.4% |
| LMArena Coding | 1484 | 1268 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1447 | — |
| GSO | 22.6% | — |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| MirrorCode | 8.9% | — |
| BigCodeBench Complete | — | 57.5% |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#34)
- Llama-3.3-70B-Instruct: 25.8 (#105)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| BALROG | 57% | 23% |
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| Berkeley Function Calling Leaderboard | — | 31.9% |
| 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-3.3-70B-Instruct: 14.1 (#327)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| SimpleBench | 79.6% | 19.9% |
| CritPt | 17.7% | 0% |
| LMArena Hard Prompts | 1485 | 1257 |
| DTBench | 97.1% | 59.5% |
| LMCA | 53.8% | 17.5% |
| Epoch Capabilities Index | 154.77 | 127.33 |
| ForecastBench | 59 | 58.6 |
| ARC-AGI-2 | 77.1% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| LiveBench Reasoning | — | 50.8% |
| Mystery Game Puzzles | 34% | — |
| LiveBench Data Analysis | — | 49.5% |
| LiveBench | — | 50.2% |

## Math

- Gemini 3.1 Pro Preview: 62.1 (#34)
- Llama-3.3-70B-Instruct: 15.3 (#298)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 5.1% |
| LMArena Math | 1485 | 1267 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| LiveBench Math | — | 42.2% |
| MATH Level 5 | — | 41.6% |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Llama-3.3-70B-Instruct: 30.6 (#226)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 94.4% | 47.4% |
| Vectara Hallucination Rate | 10.4% | 4.1% |
| LMArena Expert | 1485 | 1225 |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Confabulations | — | 22.8% |
| MMLU | — | 86.3% |

## Multimodal

- Gemini 3.1 Pro Preview: 37.9 (#69)
- Llama-3.3-70B-Instruct: —

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| 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-3.3-70B-Instruct: 39.9 (#220)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1477 | 1236 |
| LMArena Chinese | 1529 | 1217 |
| LMArena French | 1487 | 1281 |
| LMArena German | 1491 | 1251 |
| LMArena Japanese | 1493 | 1150 |
| LMArena Korean | 1455 | 1143 |
| LMArena Russian | 1498 | 1252 |
| LMArena Spanish | 1479 | 1270 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.0 (#32)
- Llama-3.3-70B-Instruct: 71.1 (#157)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1466 | 1242 |
| LiveBench Instruction Following | — | 82.7% |

## Long Context

- Gemini 3.1 Pro Preview: 47.4 (#18)
- Llama-3.3-70B-Instruct: 26.4 (#295)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1483 | 1256 |
| Fiction.LiveBench | — | 33.3% |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.1 (#37)
- Llama-3.3-70B-Instruct: 47.6 (#207)

| Benchmark | Gemini 3.1 Pro Preview | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1481 | 1274 |
| LMArena Creative Writing | 1482 | 1250 |
| LMArena Multi-Turn | 1488 | 1280 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
| LiveBench Language | — | 39.2% |

## FAQ

### Is Gemini 3.1 Pro Preview better than Llama-3.3-70B-Instruct?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 29× 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-3.3-70B-Instruct?

Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or Llama-3.3-70B-Instruct better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 31.0 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 128K.

### How many benchmarks do Gemini 3.1 Pro Preview and Llama-3.3-70B-Instruct share?

29 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Llama-3.3-70B-Instruct has 43.