Up to four models
Mixtral 8x22B vs Claude 3 Haiku
On the index (GPT-4 = 100), Mixtral 8x22B scores 99 and Claude 3 Haiku 95. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
9983–116
WeightsOpen
ReleasedApr 2024
Price in / out$2.0 / $6.0
Context66K
Core tests taken1 of 9
Mixtral 8x22B and Claude 3 Haiku are too close to call (4 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Mixtral 8x22B | Claude 3 Haiku |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 34.1% | 36.3% |
| MMLU (HELM runs) | 77.8% | 73.8% |
| Maths | ||
| MATH (level 5) | 24.2% | 14.9% |
| Coding | ||
| WeirdML | 3.2% | 9.8% |
| Agents | ||
| DTBench | 55.1% | 50.1% |
Tests at least two of these models have taken. Bold rows are the core tests.