Model comparison
Gemini 1.5 Pro (May 2024) vs Llama 2-13B
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 29.6 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
MetaSummary
- They share 21 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 6 categories and Llama 2-13B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 29.8.
- The biggest single-benchmark swing is DTBench: 59% for Gemini 1.5 Pro (May 2024) and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Llama 2-13B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 32.1 | 29.6 |
| Released | 2024-02-15 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 32 |
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 2-13B: 30.9 (#291)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1294 | 1062 |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), Llama 2-13B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Too close to call
Gemini 1.5 Pro (May 2024): 12.3 (#338), Llama 2-13B: 12.8 (#337)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1051 |
| DTBench | 59% | 42.2% |
| BIG-Bench Hard | 89.2% | 58.2% |
| Epoch Capabilities Index | 131.73 | 106.17 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Chess Puzzles | — | 0% |
| ForecastBench | 58.4 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Llama 2-13B: 31.1 (#229)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Math | 1315 | 1065 |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
| GSM8K | — | 36.9% |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Llama 2-13B: 28.1 (#249)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1279 | 1030 |
| MMLU | 86.9% | 55.6% |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Llama 2-13B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
| ScienceQA | — | 55.8% |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Llama 2-13B: 26.5 (#279)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1312 | 1024 |
| LMArena Chinese | 1331 | 1001 |
| LMArena French | 1302 | 1044 |
| LMArena German | 1286 | 1009 |
| LMArena Japanese | 1292 | 894 |
| LMArena Korean | 1298 | 953 |
| LMArena Russian | 1320 | 1055 |
| LMArena Spanish | 1311 | 1087 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Llama 2-13B: 53.3 (#287)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1045 |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Llama 2-13B: 32.3 (#269)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1308 | 1064 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Llama 2-13B: 29.8 (#289)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 2-13B |
|---|---|---|
| LMArena Text | 1319 | 1084 |
| LMArena Creative Writing | 1333 | 1047 |
| LMArena Multi-Turn | 1296 | 1050 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Llama 2-13B?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 29.6 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Llama 2-13B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 30.9 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Llama 2-13B share?
21 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Llama 2-13B has 32.