# Meta Llama 3.1 70B Instruct

As of October 21, 2026, Meta Llama 3.1 70B Instruct ranks #119 of 123 models overall with 24.3 ±10.8 on the LLMBenchmark Index. Llama 3.1 70B Instruct ranks #108 of 122 in reasoning, its strongest category. Meta Llama 3.1 70B Instruct costs $0.56 per million input tokens and $0.56 per million output tokens. Llama 3.1 70B Instruct was released on July 23, 2024.

Page: https://llmbenchmark.ai/models/llama-3-1-70b-instruct
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: Meta Llama
- Released: July 23, 2024
- Price per million input tokens: $0.56
- Price per million output tokens: $0.56
- Context window: 131K tokens
- Overall rank: 119 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 24.3 ±10.8 (90% margin, from 4 of 7 inputs)
- Artificial Analysis Intelligence Index: 6.6

Benchmark results (47 of 195):

- AA Intelligence Index: 6.6 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Math Index: 4.0 (source: Artificial Analysis, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 40.9% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 4.5% (source: Artificial Analysis, read October 21, 2026)
- MMLU Pro (Artificial Analysis run): 67.6% (source: Artificial Analysis, read October 21, 2026)
- LiveCodeBench (Artificial Analysis run): 23.2% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 3.0% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 34.4% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 15.2% (source: Artificial Analysis, read October 21, 2026)
- AIME 2025 (Artificial Analysis run): 4.0% (source: Artificial Analysis, read October 21, 2026)
- WeirdML: 9.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- BALROG: 27.9% (source: Epoch AI benchmarking hub, read October 21, 2026)
- GPQA Diamond (Epoch AI run): 44.2% (source: Epoch AI benchmarking hub, read October 21, 2026)
- OTIS Mock AIME: 3.6% (source: Epoch AI benchmarking hub, read October 21, 2026)
- MATH level 5: 36.7% (source: Epoch AI benchmarking hub, read October 21, 2026)
- MMLU: 80.1% (source: Epoch AI benchmarking hub, read October 21, 2026)
- DTBench: 60.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMCA: 14.8% (source: Epoch AI benchmarking hub, read October 21, 2026)
- TheAgentCompany: 6.9% (source: Epoch AI benchmarking hub, read October 21, 2026)
- Epoch Capabilities Index: 125.9 (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMArena Text: 1261 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: coding: 1260 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts: 1241 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: math: 1252 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: instruction following: 1231 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: creative writing: 1232 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: English: 1294 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: non-English: 1219 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Chinese: 1215 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: German: 1222 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Japanese: 1132 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Korean: 1140 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: French: 1262 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Spanish: 1253 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Russian: 1234 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: multi-turn: 1256 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: longer queries: 1241 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: expert: 1209 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts in English: 1261 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: software and IT: 1260 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: mathematical work: 1253 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: science: 1276 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: medicine and healthcare: 1257 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: legal and government: 1283 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: business and finance: 1235 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: writing and language: 1236 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: entertainment and media: 1230 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)