Llama 3-8B
ECI#205
116Llama 3-8B is an open-weights model from Meta AI, released April 18, 2024. It has an ECI score of 116 and ranks 205th of 249 tracked models. At the time of its release, it ranked 19th of 56 tracked models. At $0.04/Mtok for input tokens and $0.04/Mtok for output tokens, it is less expensive per token than similarly-capable models.
Input price$0.04 / 1M tokens
Output price$0.04 / 1M tokens
Parameters8.0e9
Training compute7.2e23 FLOP
Llama 3-8B vs select alternatives
Reasoning
| Domain | Benchmark | Llama 3-8B | |||
|---|---|---|---|---|---|
ECI scoreBest score 166 | 116 | 114 | 117 | 118 | |
| Ranking | #205 | #208 | #201 | #198 | |
| Conceptual reasoning | DTBenchBest score 98.4% | ||||
| Games | Chess PuzzlesBest score 72.0% | ||||
| Language understanding | Adversarial NLIBest score 58.1% | ||||
| Long context | ForecastBenchBest score 62.5 | 58.6 | 51.4 | — | 53.2 |
| Mathematics | MATH Level 5Best score 98.1% | ||||
OTIS Mock AIME 2024-2025Best score 100.0% | |||||
| Science | ARC AI2Best score 95.3% | ||||
GPQA DiamondBest score 95.8% | |||||
| World knowledge | MMLUBest score 88.1% |
