Llama 3 8B Instruct
Llama / Meta
34scores
28benchmarks
$0.03 / $0.04 per 1M tokenscost in/out
Metadata
Llama Open source
Aliases: llama-3-8b-instruct, meta-llama-llama-3-8b-instruct, meta-llama/llama-3-8b-instruct
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| RewardBench | Alignment | 145 | 64.50 | 2026-05-06 |
| BigCodeBench | Coding | 102 | 31.90 | 2026-05-06 |
| ENAMEL | Coding | 12 | 0.34 | 2026-05-06 |
| McEval | Coding | 13 | 36% | 2026-05-27 |
| NeoEvalPlusN | Creative | 90 | 13.75 | 2026-05-06 |
| Open FinLLM Leaderboard | Finance | 15 | 18.930312% | 2026-05-27 |
| MixEval Chat | General Knowledge | 27 | 45.60 | 2026-05-06 |
| Open LLM Leaderboard v2 | General Knowledge | 1868 | 23.91 | 2026-05-06 |
| Open LLM Leaderboard v2 | General Knowledge | 2570 | 20.61 | 2026-05-06 |
| CyberSecEval | Generalization | 7 | 45.27% | 2026-05-27 |
| L-Eval | Generalization | 3 | 58.71% | 2026-05-27 |
| WildBench | Generalization | 46 | 6.658846529814272 | 2026-05-27 |
| MuSR | Intelligence | 3367 | 5.40 | 2026-05-06 |
| MuSR | Intelligence | 4271 | 1.60 | 2026-05-06 |
| ANLI | Language | 3 | 57.30 | 2026-05-06 |
| AraGen v3 | Language | 62 | 9.21 | 2026-05-06 |
| Open Japanese LLM Leaderboard | Language | 467 | 49.62 | 2026-05-06 |
| Open Japanese LLM Leaderboard | Language | 763 | 21.64 | 2026-05-06 |
| Open Portuguese LLM Leaderboard | Language | 233 | 82.06 | 2026-05-06 |
| WinoGrande | Language | 6 | 83.50 | 2026-05-06 |
| BABILong | Long Context | 22 | 30.67 | 2026-05-06 |
| MATH Level 5 | Math | 2511 | 9.14 | 2026-05-06 |
| MATH Level 5 | Math | 2579 | 8.69 | 2026-05-06 |
| OTIS Mock AIME 2024-2025 | Mathematics | 37 | 4.31 | 2026-05-06 |
| Open Medical-LLM Leaderboard | Medical | 66 | 68.99 | 2026-05-06 |
| BenchBench | Meta | 75 | 0.44 | 2026-05-06 |
| YALL Nous Leaderboard | Reasoning | 93 | 51.24 | 2026-05-06 |
| ZebraLogic | Reasoning | 52 | 11.90 | 2026-05-06 |
| AI-Secure LLM Trustworthy Leaderboard | Safety | 3 | 0.81 | 2026-05-06 |
| ChemBench | Science | 37 | 0.46 | 2026-05-06 |
| ChemBench | Science | 38 | 0.46 | 2026-05-06 |
| StructEval | Structured Output | 11 | 51.59% | 2026-05-28 |
| VNTL Leaderboard | Translation | 72 | 60.19 | 2026-05-06 |
| VNTL Leaderboard | Translation | 82 | 55.03 | 2026-05-06 |
No matching rows.