Llama-3.3-70B-Instruct
| Released | 2024-12-06 |
|---|---|
| Price per 1M | $0.72 in · $0.72 out |
| Overall score | 35.0 · rank 218 |
| Context window | 128,000 tokens |
| Provider | Meta |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 35.0 | 218 | 9 |
| Overall: Coding | 33.6 | 217 | 6 |
| Overall: Reasoning | 36.2 | 214 | 5 |
| Overall: Agentic work | 35.5 | 214 | 6 |
| Overall: Frontend | 31.8 | 214 | 1 |
| Coding | 31.8 | 202 | 1 |
| Agents | 36.4 | 169 | 2 |
| Reasoning | 38.1 | 206 | 3 |
| Math | 33.7 | 186 | 2 |
| General | 36.9 | 170 | 1 |
| Value vs price | −11.8 | 182 |
Evidence
Coding 31.8 ±4.7
Agents 36.4 ±3.2
Reasoning 38.1 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 47.4% | Epoch AI | 2025-01-27 |
| CritPt | 0.0% | Epoch AI | 2026-11-11 |
| SimpleBench | 19.9% | SimpleBench | 2026-11-11 |
| SimpleBench | 19.9% | Epoch AI | 2026-11-11 |
Math 33.7 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 41.6% | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 5.1% | Epoch AI | 2025-02-25 |
General 36.9 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,318 | LMArena | 2026-11-09 |
Names matched to this model
llama-3-3-70b, llama-3-3-70b-instruct, llama-3-3-70b-instruct-q8, llama3-3-70b-instruct-q8