Up to four models
Llama 2 vs Gemini 1.0 Pro
On the index (GPT-4 = 100), Llama 2 scores 95 and Gemini 1.0 Pro 93. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Llama 2 and Gemini 1.0 Pro are too close to call (2 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Llama 2 | Gemini 1.0 Pro |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 26.3% | 34.0% |
| MMLU (HELM runs) | 69.5% | 70.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 0.0% | 1.1% |
| MATH (level 5) | 3.3% | 11.2% |
| Agents | ||
| DTBench | 41.6% | 45.9% |
Tests at least two of these models have taken. Bold rows are the core tests.