Llama-2-70b-chat-hf: benchmark scores, price and ranking

Llama-2-70b-chat-hf from Meta AI ranks #692 of 743 LLMs on the LLMs Tiger aggregate benchmark score (42.9), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Meta AI
Type: Open-weight / local model
Open weights: Yes
Released: 2023-07-18 (source: epoch)
Cheapest API price: $1.00 in / $1.00 out per million tokens (via anyscale, observed 2026-10-13T20:47Z)
Aggregate rank: #692 of 743 (score 42.9)

Across the 2 benchmarks where at least ten models are scored, Llama-2-70b-chat-hf is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $1.00 per million tokens, is lower than that of 35% of the 427 models with a listed price.

Llama-2-70b-chat-hf benchmark results

Llama-2-70b-chat-hf benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
GPQA Diamond	26.3%	#263 of 275	Epoch AI Benchmarking Hub	2026-10-13
OTIS Mock AIME	0.0%	#189 of 189	Epoch AI Benchmarking Hub	2026-10-13

About Llama-2-70b-chat-hf

Llama-2-70b-chat-hf is an open-weight model that can run on your own hardware from Meta AI. It was released on 2023-07-18, according to Epoch AI. The cheapest API listing we track charges $1.00 per million input tokens and $1.00 per million output tokens, through anyscale. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.

Where Llama-2-70b-chat-hf stands

On our aggregate score, Llama-2-70b-chat-hf is #692 of 743 ranked models, in the lower half. Its score is 42.9; the scale is centred on 50, so it sits 7.1 points below the typical model. That beats 7% of the ranked field. Among the 28 ranked Meta AI models it is #19. The next one up is Llama-3.1-405B-Instruct at 43.6. The next one down is Llama-3.1-70B-Instruct at 42.6.

Llama-2-70b-chat-hf, benchmark by benchmark

GPQA Diamond is a weak spot. Llama-2-70b-chat-hf scores 26.3%, #263 of 275, behind 95% of the models measured. The leader, GPT-6 Astra (max), reaches 95.8%. It covers expert-level science questions. The board median is 71.7%, so Llama-2-70b-chat-hf is 45.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

OTIS Mock AIME is a weak spot. Llama-2-70b-chat-hf scores 0.0%, #189 of 189, behind 99% 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-2-70b-chat-hf is 57.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 2% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#263 of 275) and its weakest is OTIS Mock AIME (#189 of 189).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Llama-2-70b-chat-hf costs more 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 o3-mini (high) ($1.10) and Mistral Medium 3.5 ($1.50).

Release history

The Meta AI model released before it was Llama-2-70b-chat on 2023-07-18, which scores 45.3. The next one was Meta-Llama-3-70B-Instruct on 2024-04-18, at 42.5.

Reading these numbers

The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#689 GPT-4.1 mini (43.0)
#690 GPT-3.5 (43.0)
#691 gemma-2-9b-it (43.0)
#693 SmolLM2-1.7B (42.9)
#694 mistral-large-2402 (42.8)
#695 gemini-1.5-flash-002 (42.8)