Mistral-7B-Instruct-v0.2
Mistral-7B-Instruct-v0.2 ranks first on CyberMetric.
27
Benchmarks with a score
1
Ranked first, out of five or more models
2
In the top three
Mistral AI Dec 2023 Mistral-7B-Instruct-v0.2
Open weights Small
No Epoch Capabilities Index score yet
- TOMG-Bench 4.81% #4 /5
- Open Arabic LLM Leaderboard v1 43.5% #29 /55
- AraGen 0.48% #42 /42
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 | |
|---|---|---|---|---|
| MT-Bench-101 | 6.95 | #3 of 6 | Official leaderboard | |
| Open Arabic LLM Leaderboard v1 | 43.5% | #29 of 55 | Official leaderboard | |
| MuSR | 39.7% | #60 of 98 | Official leaderboard | |
| EQ-Bench v2 | 68.2 | #57 of 85 | Official leaderboard | |
| RepoQA | 47.4% | #17 of 22 | Official leaderboard | |
| WildBench | 30.7 | #39 of 47 | Official leaderboard | |
| BABILong | 48.7% | #5 of 6 | Official leaderboard | |
| MixEval | 70% | #29 of 34 | Official leaderboard | |
| MMLU-Pro | 30.8% | #181 of 212 | Official leaderboard | |
| Chinese SimpleQA | 15.6% | #24 of 27 | Official leaderboard | |
| RULER | 68.4% | #14 of 15 | Official leaderboard | |
| Stick to Your Role! | 0.12 | #14 of 15 | Official leaderboard | |
| AraGen | 0.48% | #42 of 42 | Official leaderboard | |
| TableBench | 11% | #10 of 10 | Official leaderboard | |
| LongBench-Chat | 5.84 | #2 of 2 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HumanEval+ | 36% | #37 of 46 | Official leaderboard | |
| HumanEval | 42.1% | #38 of 46 | Official leaderboard | |
| MBPP | 44.7% | #32 of 35 | Official leaderboard | |
| MBPP+ | 37% | #32 of 35 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 15 | #174 of 188 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AfriMed-QA | 58.4% | #4 of 4 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberMetric | 74.8% | #1 of 10 | Official leaderboard | |
| PrivacyLens | 33.5% | #2 of 4 | Official leaderboard | |
| TOMG-Bench | 4.81% | #4 of 5 | Official leaderboard | |
| SORRY-Bench | 67% | #21 of 23 | Official leaderboard | |
| SALAD-Bench | 80.1% | #12 of 13 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 18.5 | #58 of 99 | Official leaderboard |