# Gemini 3 Flash Preview vs Llama 3.1-405B

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-flash-preview-vs-llama-3-1-405b
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3 Flash Preview leads 51.4 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 52.3 | 30.4 |
| Rank | 33 | 279 |
| Context | 1.05M | — |
| Input $/M | $0.50 | — |
| Output $/M | $3 | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 3 Flash Preview: 51.5 (#35)
- Llama 3.1-405B: 32.7 (#257)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| WeirdML | 61.6% | 21.4% |
| LMArena Coding | 1460 | 1291 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| ALE-Bench | 1,367 | — |

## Agentic & Tool Use

- Gemini 3 Flash Preview: 38.6 (#27)
- Llama 3.1-405B: 20.9 (#131)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| TheAgentCompany | — | 7.4% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| Cybench | — | 7.5% |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |

## Reasoning

- Gemini 3 Flash Preview: 49.2 (#35)
- Llama 3.1-405B: 16.4 (#293)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 61.1% | 23% |
| LMArena Hard Prompts | 1465 | 1270 |
| DTBench | 89.1% | 61.4% |
| Epoch Capabilities Index | 151.83 | 128.76 |
| ForecastBench | 58.5 | 59.9 |
| ARC-AGI-2 | 33.6% | — |
| Kagi LLM Benchmark | — | 45% |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 26% | — |
| LMCA | 43.1% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |

## Math

- Gemini 3 Flash Preview: 51.4 (#42)
- Llama 3.1-405B: 17.3 (#283)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 9.7% |
| LMArena Math | 1472 | 1281 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 3 Flash Preview: 58.8 (#30)
- Llama 3.1-405B: 30.4 (#221)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 89.4% | 50.9% |
| LMArena Expert | 1461 | 1243 |
| SimpleQA Verified | 66.8% | — |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| Vectara Hallucination Rate | 13.5% | — |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |

## Multimodal

- Gemini 3 Flash Preview: 45.3 (#15)
- Llama 3.1-405B: —

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |

## Multilingual

- Gemini 3 Flash Preview: 55.9 (#26)
- Llama 3.1-405B: 40.9 (#209)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1458 | 1248 |
| LMArena Chinese | 1510 | 1242 |
| LMArena French | 1478 | 1278 |
| LMArena German | 1497 | 1252 |
| LMArena Japanese | 1488 | 1208 |
| LMArena Korean | 1443 | 1184 |
| LMArena Russian | 1480 | 1265 |
| LMArena Spanish | 1470 | 1259 |

## Instruction Following

- Gemini 3 Flash Preview: 75.8 (#52)
- Llama 3.1-405B: 66.1 (#209)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1437 | 1259 |
| IFEval | — | 81.1% |

## Long Context

- Gemini 3 Flash Preview: 44.4 (#63)
- Llama 3.1-405B: 38.4 (#192)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1452 | 1266 |

## Writing & Preference

- Gemini 3 Flash Preview: 65.6 (#44)
- Llama 3.1-405B: 39.1 (#246)

| Benchmark | Gemini 3 Flash Preview | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1466 | 1284 |
| LMArena Creative Writing | 1457 | 1262 |
| LMArena Multi-Turn | 1471 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |

## FAQ

### Is Gemini 3 Flash Preview better than Llama 3.1-405B?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.4 on the Noometry Index.

### Is Gemini 3 Flash Preview or Llama 3.1-405B better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 32.7 in the Noometry coding category.

### How many benchmarks do Gemini 3 Flash Preview and Llama 3.1-405B share?

24 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Llama 3.1-405B has 42.