Model comparison
Gemini 3.1 Flash Lite vs Llama 3.1-405B
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 30.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
MetaSummary
- They share 24 benchmarks with published results for both. Gemini 3.1 Flash Lite 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 3.1 Flash Lite leads 39.5 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for Gemini 3.1 Flash Lite and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 40.4 | 30.4 |
| Released | 2026-03-03 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 38 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 37.5 (#179), Llama 3.1-405B: 32.7 (#257)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| WeirdML | 52.2% | 21.4% |
| LMArena Coding | 1400 | 1291 |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| ALE-Bench | 797.73 | — |
Agentic & Tool Use Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 29.9 (#72), Llama 3.1-405B: 20.9 (#131)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| DeepResearch Bench | 37.3% | — |
Reasoning Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 22.3 (#181), Llama 3.1-405B: 16.4 (#293)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 45% |
| LMArena Hard Prompts | 1407 | 1270 |
| DTBench | 76.8% | 61.4% |
| Epoch Capabilities Index | 144.45 | 128.76 |
| ForecastBench | 54.4 | 59.9 |
| SimpleBench | — | 23% |
| NYT Connections (extended) | 8.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| LMCA | 35% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 39.5 (#82), Llama 3.1-405B: 17.3 (#283)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 9.7% |
| LMArena Math | 1427 | 1281 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.7 (#95), Llama 3.1-405B: 30.4 (#221)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 81.8% | 50.9% |
| LMArena Expert | 1397 | 1243 |
| Humanity's Last Exam | 8.6% | — |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 38.7 (#57), Llama 3.1-405B: —
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.5 (#82), Llama 3.1-405B: 40.9 (#209)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1410 | 1248 |
| LMArena Chinese | 1461 | 1242 |
| LMArena French | 1423 | 1278 |
| LMArena German | 1429 | 1252 |
| LMArena Japanese | 1411 | 1208 |
| LMArena Korean | 1393 | 1184 |
| LMArena Russian | 1420 | 1265 |
| LMArena Spanish | 1420 | 1259 |
Instruction Following Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 72.9 (#126), Llama 3.1-405B: 66.1 (#209)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1376 | 1259 |
| IFEval | — | 81.1% |
Long Context Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 42.5 (#117), Llama 3.1-405B: 38.4 (#192)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1394 | 1266 |
Writing & Preference Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 61.0 (#90), Llama 3.1-405B: 39.1 (#246)
| Benchmark | Gemini 3.1 Flash Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1416 | 1284 |
| LMArena Creative Writing | 1401 | 1262 |
| LMArena Multi-Turn | 1417 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Llama 3.1-405B?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 30.4 on the Noometry Index.
Is Gemini 3.1 Flash Lite or Llama 3.1-405B better for coding?
Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.5 versus 32.7 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Flash Lite and Llama 3.1-405B share?
24 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Llama 3.1-405B has 42.