Llama 3-70B
| Released | 2024-04-18 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 32.4 (early, few results) |
| Provider | Meta |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 32.4 | 5 | |
| Overall: Coding | 34.5 | 2 | |
| Overall: Reasoning | 32.9 | 4 | |
| Overall: Agentic work | 34.5 | 2 | |
| Reasoning | 34.5 | 2 | |
| Math | 30.7 | 2 | |
| General | 31.0 | 1 |
Evidence
Reasoning 34.5 ±4.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 40.6% | Epoch AI | 2025-01-27 |
| Kagi Reasoning Benchmark | 35.1% | Kagi | 2026-11-11 |
Math 30.7 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 22.6% | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 4.3% | Epoch AI | 2025-02-25 |
General 31.0 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,277 | LMArena | 2026-11-09 |
Names matched to this model
llama-3-70b, meta-llama-3-70b, meta-llama-3-70b-instruct