Model comparison
Gemini 1.5 Pro (May 2024) vs Llama 3.1-405B
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 30.7 on the Noometry Index.
Last verified . 35 shared benchmarks.
Google
MetaSummary
- They share 35 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 6 categories and Llama 3.1-405B in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 38.9.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 49.8% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 32.1 | 30.7 |
| Released | 2024-02-15 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| WeirdML | 22.2% | 21.4% |
| LMArena Coding | 1294 | 1291 |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Llama 3.1-405B leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | 3.4% | 7.4% |
| Cybench | 7.5% | 7.5% |
| BALROG | 21% | — |
Reasoning Llama 3.1-405B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 27.1% | 23% |
| LMArena Hard Prompts | 1296 | 1269 |
| DTBench | 59% | 61.4% |
| BIG-Bench Hard | 89.2% | 82.9% |
| Epoch Capabilities Index | 131.73 | 128.75 |
| ForecastBench | 58.4 | 59.9 |
| ARC-AGI-2 | 0.8% | — |
| Kagi LLM Benchmark | — | 45% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 9.7% |
| Omni-MATH | 36.4% | 24.9% |
| LMArena Math | 1315 | 1281 |
| MATH Level 5 | 70.4% | 49.8% |
Knowledge Llama 3.1-405B leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 57.2% | 50.9% |
| MMLU-Pro | 73.7% | 72.3% |
| Confabulations | 13.5% | 17.6% |
| GPQA (HELM) | 53.4% | 52.2% |
| LMArena Expert | 1279 | 1243 |
| MMLU | 86.9% | 84.5% |
| Humanity's Last Exam | 4.6% | — |
| ARC (AI2) Challenge | — | 95.3% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Llama 3.1-405B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1312 | 1248 |
| LMArena Chinese | 1331 | 1242 |
| LMArena French | 1302 | 1279 |
| LMArena German | 1286 | 1252 |
| LMArena Japanese | 1292 | 1208 |
| LMArena Korean | 1298 | 1184 |
| LMArena Russian | 1320 | 1265 |
| LMArena Spanish | 1311 | 1260 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| IFEval | 83.7% | 81.1% |
| LMArena Instruction Following | 1297 | 1259 |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1308 | 1266 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1319 | 1284 |
| LMArena Creative Writing | 1333 | 1262 |
| WildBench | 81.3% | 78.3% |
| LMArena Multi-Turn | 1296 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Llama 3.1-405B?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 30.7 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Llama 3.1-405B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 33.1 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Llama 3.1-405B share?
35 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Llama 3.1-405B has 42.