Llama 2-Chat helpfulness human evaluation (Meta)
Only in system cards
Three human raters compare Llama 2-Chat with a rival chat model on about 4,000 single and multi-turn helpfulness prompts.
In-house Meta evaluation. Results are win, tie and loss rates against one rival per model size.
Made by Meta Released Jul 2023 Overall chat quality Tasks kept private Last in a system card Jul 2023
Last model added Jul 2023
- Scored
- Ranked by votes People pick the better of two answers, as in an arena, and the votes are turned into ratings.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
4
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Llama 2-Chat helpfulness human evaluation (Meta) yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
4 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 19 Jul 2023 |  Llama 2-7B technical report | Llama 2-Chat 7B vs MPT-7B-chat, win/tie/loss chart with no printed values (Figure 12). Text: wins on 60% of prompts | Capabilities | |
| 19 Jul 2023 | Llama 2-70B technical report | Llama 2-Chat 70B vs PaLM-Bison and ChatGPT-0301, chart with no printed values (Figure 12). Text: 36% win and 31.5% tie vs ChatGPT | Capabilities | |
| 19 Jul 2023 | Llama 2-34B technical report | Llama 2-Chat 34B vs Vicuna-33b-v1.3 and Falcon-40b-instruct, chart with no printed values (Figure 12). Text: overall win rate above 75% | Capabilities | |
| 19 Jul 2023 | Llama 2-13B technical report | Llama 2-Chat 13B vs Vicuna-13b-v1.1, win/tie/loss chart with no printed values (Figure 12) | Capabilities |
More in Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9% - IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose).
Nemotron-Cascade 2 30B-A3B 82.9% - MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85% - IFStruct In use Models generate JSON or YAML that must follow a requested schema and phrasing constraints, without constrained decoding. A response passes only if every structural constraint holds. LFM3-1.7B 93.7%