Up to four models
Phi-3 vs Claude 2.1
On the index (GPT-4 = 100), Phi-3 scores 97 and Claude 2.1 96. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Phi-3 and Claude 2.1 are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Phi-3 | Claude 2.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 27.6% | 33.0% |
| MMLU (HELM runs) | 77.5% | 73.5% |
Tests at least two of these models have taken. Bold rows are the core tests.