Llama-3.1-Tulu-3-70B-DPO: benchmark scores, price and ranking
Llama-3.1-Tulu-3-70B-DPO from Allen Institute for AI,University of Washington ranks #621 of 743 LLMs on the LLMs Tiger aggregate benchmark score (44.8), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- Allen Institute for AI,University of Washington
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2024-11-21 (source: epoch)
- Aggregate rank
- #621 of 743 (score 44.8)
Across the 2 benchmarks where at least ten models are scored, Llama-3.1-Tulu-3-70B-DPO is in the top 10% on 0 and in the top half on 0.
Llama-3.1-Tulu-3-70B-DPO benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 46.3% | #203 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 4.4% | #160 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Llama-3.1-Tulu-3-70B-DPO
Llama-3.1-Tulu-3-70B-DPO is an open-weight model that can run on your own hardware from Allen Institute for AI,University of Washington. It was released on 2024-11-21, according to Epoch AI. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where Llama-3.1-Tulu-3-70B-DPO stands
On our aggregate score, Llama-3.1-Tulu-3-70B-DPO is #621 of 743 ranked models, in the lower half. Its score is 44.8; the scale is centred on 50, so it sits 5.2 points below the typical model. That beats 16% of the ranked field.
Llama-3.1-Tulu-3-70B-DPO, benchmark by benchmark
Llama-3.1-Tulu-3-70B-DPO lands below the middle on GPQA Diamond: 46.3%, #203 of 275, with 73% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is gpt-4-turbo-2024-04-09 at 46.6%. It covers expert-level science questions. The board median is 71.7%, so Llama-3.1-Tulu-3-70B-DPO is 25.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
OTIS Mock AIME is a weak spot. Llama-3.1-Tulu-3-70B-DPO scores 4.4%, #160 of 189, behind 84% 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-Tulu-3-70B-DPO is 53.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 21% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#203 of 275) and its weakest is OTIS Mock AIME (#160 of 189).
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
- #618 Qwen3.5 9B (44.9)
- #619 granite-3.1-8b-base (44.9)
- #620 GPT-4.1 (44.9)
- #622 o1-mini-2024-09-12 (44.8)
- #623 mistral-small-2501 (44.8)
- #624 Qwen2.5-1.5B (44.7)
Compare it on the live leaderboard → · How the aggregate score works