Up to four models
Claude 2 vs Ministral 8B
On the index (GPT-4 = 100), Claude 2 scores 94 and Ministral 8B 93. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude 2 and Ministral 8B are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
Claude 2
Ministral 8B
Every result as a table
| Test | Claude 2 | Ministral 8B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 34.7% | 27.2% |
| Maths | ||
| MATH (level 5) | 11.7% | 14.9% |
| Agents | ||
| DTBench | 51.8% | 45.7% |
Tests at least two of these models have taken. Bold rows are the core tests.