WizardLM-2 8x22B
WizardLM-2 8x22B.
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Microsoft Apr 2024 WizardLM-2 8x22B
Open weights
No Epoch Capabilities Index score yet
- GPQA Diamond 43.4% #179 /229
- MATH Level 5 25.7% #68 /94
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| EQ-Bench v2 | 77.9 | #29 of 85 | Official leaderboard | |
| AlignBench | 7.34 | #5 of 7 | Official leaderboard | |
| MMLU-Pro | 39.2% | #164 of 212 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 11.7% | #135 of 148 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH Level 5 | 25.7% | #68 of 94 | Epoch AI run | |
| GPQA Diamond | 43.4% | #179 of 229 | Epoch AI run |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Aider-Edit | 44.4% | #33 of 34 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 16 | #165 of 188 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| nocot-bench (NCRI) | 73.2 | #82 of 185 | Official leaderboard |