Llama 3-8B
| Released | 2024-04-18 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 25.6 (early, few results) |
| Provider | Meta |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 25.6 | 4 | |
| Overall: Coding | 27.4 | 1 | |
| Overall: Reasoning | 26.4 | 3 | |
| Overall: Agentic work | 27.4 | 1 | |
| Reasoning | 27.4 | 1 | |
| Math | 25.1 | 2 | |
| General | 23.5 | 1 |
Evidence
Reasoning 27.4 ±4.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 26.1% | Epoch AI | 2025-01-27 |
Math 25.1 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 6.1% | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 1.9% | Epoch AI | 2026-08-30 |
General 23.5 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,224 | LMArena | 2026-11-09 |
Names matched to this model
llama-3-8b, meta-llama-3-8b, meta-llama-3-8b-instruct