Llama-3.1-70B-Instruct: benchmark scores, price and ranking
Llama-3.1-70B-Instruct from Meta AI ranks #700 of 743 LLMs on the LLMs Tiger aggregate benchmark score (42.6), based on 8 benchmark results captured up to 2026-10-13.
- Organisation
- Meta AI
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2024-07-23 (source: epoch)
- Cheapest API price
- $0.400 in / $0.400 out per million tokens (via openrouter, observed 2026-10-13T19:47Z)
- Aggregate rank
- #700 of 743 (score 42.6)
Relative to other models, Llama-3.1-70B-Instruct is strongest on Aider Code Editing (#39 of 92) and weakest on WeirdML (#105 of 109).
Across the 8 benchmarks where at least ten models are scored, Llama-3.1-70B-Instruct is in the top 10% on 0 and in the top half on 2.
Its cheapest listed input price, $0.400 per million tokens, is lower than that of 53% of the 427 models with a listed price.
Llama-3.1-70B-Instruct benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Aider Code Editing | 58.6% | #39 of 92 | Aider Aider Code Editing leaderboard | 2026-10-13 |
| BALROG | 27.9% | #17 of 34 | Epoch AI Benchmarking Hub | 2026-10-13 |
| TheAgentCompany | 6.9% | #9 of 13 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 60.0% | #103 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 44.2% | #211 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 14.8% | #88 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 3.6% | #165 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 9.0% | #105 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Llama-3.1-70B-Instruct
Llama-3.1-70B-Instruct is an open-weight model that can run on your own hardware from Meta AI. It was released on 2024-07-23, according to Epoch AI. The cheapest API listing we track charges $0.400 per million input tokens and $0.400 per million output tokens, through openrouter. We hold 8 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where Llama-3.1-70B-Instruct stands
On our aggregate score, Llama-3.1-70B-Instruct is #700 of 743 ranked models, in the lower half. Its score is 42.6; the scale is centred on 50, so it sits 7.4 points below the typical model. That beats 6% of the ranked field. Among the 28 ranked Meta AI models it is #20. The next one up is Llama-2-70b-chat-hf at 42.9. The next one down is Meta-Llama-3-70B-Instruct at 42.5.
Llama-3.1-70B-Instruct, benchmark by benchmark
Aider Code Editing puts Llama-3.1-70B-Instruct at 58.6%, #39 of 92. That beats 58% of the models tested, but 25.6 points short of Claude 3.5-Sonnet-20241022 (84.2%). The results either side are Grok-2 (58.6%) and ollama/qwen2.5:32b-instruct-q8_0 (58.6%). It covers Aider official benchmark. The board median is 55.6%, so Llama-3.1-70B-Instruct is 3.0 points above it. Source: Aider Aider Code Editing leaderboard, captured 2026-10-13.
On BALROG, Llama-3.1-70B-Instruct reaches 27.9%. It ranks #17 of 34, ahead of 50% of the field, and 40.4 points behind GPT-6 Astra (max) at 68.3%. The results either side are Reka Flash 3 (29.2%) and Llama-3.2-90B-Vision-Instruct (27.3%). It covers long-horizon game-playing agents. The board median is 27.6%, so Llama-3.1-70B-Instruct is 0.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama-3.1-70B-Instruct lands below the middle on TheAgentCompany: 6.9%, #9 of 13, with 62% of the field scoring higher. gemini-2.5-flash-preview-09-2025 leads at 41.1%; the closest result above is Llama-3.1-405B-Instruct at 7.4%. It covers work tasks in a simulated software company. The board median is 8.6%, so Llama-3.1-70B-Instruct is 1.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama-3.1-70B-Instruct lands below the middle on DTBench: 60.0%, #103 of 146, with 70% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is Qwen3-30B-A3B at 60.3%. It covers dynamic tool-use benchmark. The board median is 68.8%, so Llama-3.1-70B-Instruct is 8.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama-3.1-70B-Instruct lands below the middle on GPQA Diamond: 44.2%, #211 of 275, with 76% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is DeepSeek-R1-Distill-Qwen-14B at 44.7%. It covers expert-level science questions. The board median is 71.7%, so Llama-3.1-70B-Instruct is 27.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMCA is a weak spot. Llama-3.1-70B-Instruct scores 14.8%, #88 of 108, behind 81% of the models measured. The leader, Claude Opus 5.5 (max), reaches 68.2%. It covers language-model capability assessment. The board median is 29.2%, so Llama-3.1-70B-Instruct is 14.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
OTIS Mock AIME is a weak spot. Llama-3.1-70B-Instruct scores 3.6%, #165 of 189, behind 87% of the models measured. The leader, Claude Fable 5.1 (max), reaches 100.0%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Llama-3.1-70B-Instruct is 54.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
WeirdML is a weak spot. Llama-3.1-70B-Instruct scores 9.0%, #105 of 109, behind 95% of the models measured. The leader, GPT-6 Astra (max), reaches 93.3%. It covers unusual machine-learning tasks. The board median is 41.2%, so Llama-3.1-70B-Instruct is 32.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 18% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#211 of 275) and its weakest is OTIS Mock AIME (#165 of 189). Agents and tool use: uneven, ahead of 37% of the field on average across 3 benchmarks. Its best board here is BALROG (#17 of 34) and its weakest is DTBench (#103 of 146). General knowledge and chat: weak, ahead of 11% of the field on average across 2 benchmarks. Its best board here is LMCA (#88 of 108) and its weakest is WeirdML (#105 of 109).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Llama-3.1-70B-Instruct costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Mistral Large 3 ($0.500) and Mixtral-8x22B-Instruct-v0.1 ($0.600).
Release history
The Meta AI model released before it was Llama 3.1-70B on 2024-07-23, which scores 47.5. The next one was Llama 3.1-8B on 2024-07-23, at 45.3.
Reading these numbers
The 8 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (7), Aider Aider Code Editing leaderboard (1). 1 of them come from an official leaderboard and 7 from datasets or third-party runs.
Models ranked nearby
- #697 Mistral Large 3 (42.7)
- #698 granite-4.0-1b (42.7)
- #699 Qwen2.5-Coder-0.5B-Instruct (42.6)
- #701 Gemini 1.5 Flash (May 2024) (42.6)
- #702 gpt-4-turbo-2024-04-09 (42.6)
- #703 ministral-8b-2410 (42.6)
More from Meta AI
- Muse Spark 1.3 (max) (#18, 55.1)
- Muse Spark (#29, 53.7)
- Muse Spark 1.1 (xhigh) (#66, 52.4)
- Muse Spark 1.2 (xhigh) (#113, 51.5)
- Llama 3.1-405B (#142, 51.2)
- Muse Wonder (max) (#209, 50.1)
Compare it on the live leaderboard → · How the aggregate score works