Allen Institute for AI (Ai2), open weights

# Tulu 3 (Tülu 3) 70B

> Tulu 3 (Tülu 3) 70B by Allen Institute for AI (Ai2), released November 2024. Ranked #251 of 354 with a Noometry Index of 33.0. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/tulu-3-70b
- Last updated: 2026-10-10
- Title: Tulu 3 (Tülu 3) 70B Benchmarks, Price & Rank (October 2026)

Tulu 3 (Tülu 3) 70B by Allen Institute for AI (Ai2) ranks 251st of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.0. Its strongest category is reasoning, where it ranks 169th.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #251 of 354
- **Index score:** 33.0
- **Evidence:** Confirmed 14 results
- **Provider:** [![](/logos/ai2.svg) Allen Institute for AI (Ai2)](https://noometry.com/providers/ai2)
- **Released:** November 21, 2024
- **Weights:** Open weights
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** Not measured
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

Each category score combines every public result we have in that category.

Tulu 3 (Tülu 3) 70B category scores

1.  Coding 36.0
2.  Reasoning 23.9
3.  Math 14.2
4.  Knowledge 25.0
5.  Multilingual 39.9
6.  Instruction Following 64.8
7.  Long Context 37.1
8.  Writing & Preference 45.6
9.  020406080

Tulu 3 (Tülu 3) 70B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 36.0 | #214 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 23.9 | #169 | 1 |
| [Math](https://noometry.com/best/math) | 14.2 | #303 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 25.0 | #264 | 1 |
| [Multilingual](https://noometry.com/best/multilingual) | 39.9 | #222 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 64.8 | #227 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 37.1 | #222 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 45.6 | #223 | 3 |

## Strengths and weaknesses

Categories where Tulu 3 (Tülu 3) 70B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Tulu 3 (Tülu 3) 70B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 23.9 | +0.3 | #169 of 350, top 49% |
| [Coding](https://noometry.com/best/coding) | 36.0 | −2.7 | #214 of 340, top 63% |
| [Writing & Preference](https://noometry.com/best/writing) | 45.6 | −8.2 | #223 of 312, top 72% |

### Weakest categories

Tulu 3 (Tülu 3) 70B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Math](https://noometry.com/best/math) | 14.2 | −22.4 | #303 of 327, top 93% |
| [Knowledge](https://noometry.com/best/knowledge) | 25.0 | −12.3 | #264 of 314, top 85% |
| [Long Context](https://noometry.com/best/long-context) | 37.1 | −3.8 | #222 of 296, top 75% |

## Closest competitors

The models ranked just above and below Tulu 3 (Tülu 3) 70B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Tulu 3 (Tülu 3) 70B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Granite 3.1 2b Instruct](https://noometry.com/models/granite-3-1-2b-instruct) | #247 | 33.2 | — | — | [Compare](https://noometry.com/compare/granite-3-1-2b-instruct-vs-tulu-3-70b) |
| [Gemma 2 2b IT](https://noometry.com/models/gemma-2-2b-it) | #248 | 33.1 | — | — | [Compare](https://noometry.com/compare/gemma-2-2b-it-vs-tulu-3-70b) |
| [Wizardlm 70b](https://noometry.com/models/wizardlm-70b) | #249 | 33.0 | — | — | [Compare](https://noometry.com/compare/tulu-3-70b-vs-wizardlm-70b) |
| [Phi 3 Medium 4k Instruct](https://noometry.com/models/phi-3-medium-4k-instruct) | #250 | 33.0 | — | — | [Compare](https://noometry.com/compare/phi-3-medium-4k-instruct-vs-tulu-3-70b) |
| [DeepSeek-R1-Distill-Qwen-14B](https://noometry.com/models/deepseek-r1-distill-qwen-14b) | #252 | 32.7 | — | — | [Compare](https://noometry.com/compare/deepseek-r1-distill-qwen-14b-vs-tulu-3-70b) |
| [Qwen1.5-14B](https://noometry.com/models/qwen1-5-14b) | #253 | 32.7 | — | — | [Compare](https://noometry.com/compare/qwen1-5-14b-vs-tulu-3-70b) |
| [Olmo 2 0325 32b Instruct](https://noometry.com/models/olmo-2-0325-32b-instruct) | #254 | 32.7 | — | — | [Compare](https://noometry.com/compare/olmo-2-0325-32b-instruct-vs-tulu-3-70b) |
| [gpt-oss-20b](https://noometry.com/models/gpt-oss-20b) | #255 | 32.5 | $0.036 | 96 | [Compare](https://noometry.com/compare/gpt-oss-20b-vs-tulu-3-70b) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Tulu 3 (Tülu 3) 70B Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1235 | #229 of 294, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Reasoning

Tulu 3 (Tülu 3) 70B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1220 | #229 of 297, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Math

Tulu 3 (Tülu 3) 70B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 4.4% | #150 of 173, top 87% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-03-07 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1242 | #218 of 285, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 42.7% | #50 of 79, top 64% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |

### Knowledge

Tulu 3 (Tülu 3) 70B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 46.3% | #140 of 186, top 76% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |

### Multilingual

Tulu 3 (Tülu 3) 70B Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1236 | #222 of 297, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1249 | #208 of 285, top 73% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1246 | #215 of 283, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Tulu 3 (Tülu 3) 70B Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1233 | #226 of 298, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Tulu 3 (Tülu 3) 70B Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1224 | #233 of 291, top 81% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Tulu 3 (Tülu 3) 70B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1256 | #224 of 297, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1231 | #221 of 295, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1252 | #224 of 295, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## Compare Tulu 3 (Tülu 3) 70B

-   [Tulu 3 (Tülu 3) 70B vs Phi 3 Medium 4k Instruct](https://noometry.com/compare/phi-3-medium-4k-instruct-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs DeepSeek-R1-Distill-Qwen-14B](https://noometry.com/compare/deepseek-r1-distill-qwen-14b-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Wizardlm 70b](https://noometry.com/compare/tulu-3-70b-vs-wizardlm-70b)
-   [Tulu 3 (Tülu 3) 70B vs Qwen1.5-14B](https://noometry.com/compare/qwen1-5-14b-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Gemma 2 2b IT](https://noometry.com/compare/gemma-2-2b-it-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Olmo 2 0325 32b Instruct](https://noometry.com/compare/olmo-2-0325-32b-instruct-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Qwen3.8 Max](https://noometry.com/compare/qwen3-8-max-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-tulu-3-70b)
-   [Tulu 3 (Tülu 3) 70B vs Muse Spark 1.3](https://noometry.com/compare/muse-spark-1-3-vs-tulu-3-70b)

## Other Allen Institute for AI (Ai2) models

-   [Olmo 3.1 32b Instruct](https://noometry.com/models/olmo-3-1-32b-instruct)39.4
-   [Molmo 2 8b](https://noometry.com/models/molmo-2-8b)39.1
-   [Olmo 3 32b Think](https://noometry.com/models/olmo-3-32b-think)38.7
-   [Olmo 3.1 32b Think](https://noometry.com/models/olmo-3-1-32b-think)37.9
-   [Llama 3.1 Tulu 3 8b](https://noometry.com/models/llama-3-1-tulu-3-8b)35.7
-   [Olmo 2 0325 32b Instruct](https://noometry.com/models/olmo-2-0325-32b-instruct)32.7
-   [Olmo 7b Instruct](https://noometry.com/models/olmo-7b-instruct)30.3
-   [OLMo 2 Furious 13B](https://noometry.com/models/olmo-2-furious-13b)29.7

## Frequently asked questions

### How good is Tulu 3 (Tülu 3) 70B?

Tulu 3 (Tülu 3) 70B by Allen Institute for AI (Ai2) ranks 251st of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.0. Its strongest category is reasoning, where it ranks 169th.

### Is Tulu 3 (Tülu 3) 70B open source?

Yes. Tulu 3 (Tülu 3) 70B's weights are downloadable; check the license for commercial terms.

### What are Tulu 3 (Tülu 3) 70B's strengths and weaknesses?

Relative to other ranked models, Tulu 3 (Tülu 3) 70B places best in reasoning, coding, writing & preference and lowest in math, knowledge, long context.

### What is Tulu 3 (Tülu 3) 70B best at?

Its best category is reasoning, where it ranks 169th on Noometry.

### Cite this page

Noometry. (2026). Tulu 3 (Tülu 3) 70B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/tulu-3-70b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/tulu-3-70b.md).