RLTasksby ulam.ai
Models / Reported model

Reported model / MODEL EVIDENCE

Vicuna-13B

9 benchmarks · 38 observations · 8 sources

Scores at a glance

9 benchmarks · large dot: Vicuna-13B; small dots: closest models where reported

FActScore ↗46.6%
17.373.1

Vicuna 13B · FActScore · estimator A · Unlabeled entity-biography evaluation ↗

BIPIA & InjecAgent (Indirect Prompt Injection) ↗15.31%
12.3731.03

Vicuna-13B · BIPIA & InjecAgent (Indirect Prompt Injection) · BIPIA overall attack success · black-box defense comparison ↗

2 more reported results

16.58% · Vicuna-13B · BIPIA & InjecAgent (Indirect Prompt Injection) · BIPIA overall attack success · black-box defense comparison · Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models ↗

10.21% · Vicuna-13B · BIPIA & InjecAgent (Indirect Prompt Injection) · BIPIA overall attack success · black-box defense comparison · Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models ↗

HumanEval+ ↗15.9%
1.889

Vicuna-13B · HumanEval+ · Pass@1 · EvalPlus · official result data ↗

HumanEval ↗17.1%
2.496.3

Vicuna-13B · HumanEval · Pass@1 · EvalPlus · official result data ↗

AlpacaEval ↗70.4%
15.295.3

vicuna-13b · AlpacaEval · AlpacaEval 1 · GPT-4 judged win rate · original leaderboard example ↗

HaluEval 2.0 ↗50.59%
14.6660.91

Vicuna 13B · HaluEval 2.0 · Biomedicine · MaHR · published main comparison ↗

9 more reported results

17.55% · Vicuna 13B · HaluEval 2.0 · Biomedicine · MiHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

46.19% · Vicuna 13B · HaluEval 2.0 · Finance · MaHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

13.15% · Vicuna 13B · HaluEval 2.0 · Finance · MiHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

34.44% · Vicuna 13B · HaluEval 2.0 · Science · MaHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

8.75% · Vicuna 13B · HaluEval 2.0 · Science · MiHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

55.81% · Vicuna 13B · HaluEval 2.0 · Education · MaHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

17.88% · Vicuna 13B · HaluEval 2.0 · Education · MiHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

65.43% · Vicuna 13B · HaluEval 2.0 · Open Domain · MaHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

29.15% · Vicuna 13B · HaluEval 2.0 · Open Domain · MiHR · published main comparison · The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ↗

ClinicBench ↗38%
28.483.4

Vicuna-13B · ClinicBench · MedQA · Accuracy · zero-shot main comparison ↗

16 more reported results

36.4% · Vicuna-13B · ClinicBench · MedMCQA · Accuracy · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

45.6% · Vicuna-13B · ClinicBench · MMLU · Accuracy · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

66.2% · Vicuna-13B · ClinicBench · PubMedQA · Accuracy · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

76.8% · Vicuna-13B · ClinicBench · Referral QA · Accuracy · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

4.6 F1 points · Vicuna-13B · ClinicBench · Treat Recom. · F1 · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

14.5 ROUGE-L points · Vicuna-13B · ClinicBench · MIMIC · ROUGE-L · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

9.4 ROUGE-L points · Vicuna-13B · ClinicBench · IU-Xray · ROUGE-L · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

6.2 ROUGE-L points · Vicuna-13B · ClinicBench · Hospitaliz. Summari. · ROUGE-L · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

4.7 ROUGE-L points · Vicuna-13B · ClinicBench · Patient Education · ROUGE-L · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

46.2 F1 entity-level points · Vicuna-13B · ClinicBench · BC5 · F1 entity-level · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

39 F1 entity-level points · Vicuna-13B · ClinicBench · NCBI · F1 entity-level · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

41.3 Micro F1 points · Vicuna-13B · ClinicBench · DDI · Micro F1 · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

43.5 Micro F1 points · Vicuna-13B · ClinicBench · GAD · Micro F1 · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

56.7 Micro F1 points · Vicuna-13B · ClinicBench · HoC · Micro F1 · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

45.1% · Vicuna-13B · ClinicBench · Pharma. QA · Accuracy · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

46% · Vicuna-13B · ClinicBench · Drug Inter. · Accuracy · zero-shot main comparison · Large Language Models in the Clinic: A Comprehensive Benchmark ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

GPT-4 →OpenAI
50.1 percentile-point gap

6 of 9 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Baichuan 2: Open Large-scale Language Models ↗

    Yang, Aiyuan, Xiao, Bin, Wang, Bingning, Zhang, Borong, Bian, Ce, Yin, Chao et al. · 2023

    All 55 authors

    Yang, Aiyuan, Xiao, Bin, Wang, Bingning, Zhang, Borong, Bian, Ce, Yin, Chao, Lv, Chenxu, Pan, Da, Wang, Dian, Yan, Dong, Yang, Fan, Deng, Fei, Wang, Feng, Liu, Feng, Ai, Guangwei, Dong, Guosheng, Zhao, Haizhou, Xu, Hang, Sun, Haoze, Zhang, Hongda, Liu, Hui, Ji, Jiaming, Xie, Jian, Dai, JunTao, Fang, Kun, Su, Lei, Song, Liang, Liu, Lifeng, Ru, Liyun, Ma, Luyao, Wang, Mang, Liu, Mickel, Lin, MingAn, Nie, Nuolan, Guo, Peidong, Sun, Ruiyang, Zhang, Tao, Li, Tianpeng, Li, Tianyu, Cheng, Wei, Chen, Weipeng, Zeng, Xiangrong, Wang, Xiaochuan, Chen, Xiaoxi, Men, Xin, Yu, Xin, Pan, Xuehai, Shen, Yanjun, Wang, Yiding, Li, Yiyu, Jiang, Youxin, Gao, Yuchen, Zhang, Yupeng, Zhou, Zenan, Wu, Zhiying

  2. Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models — published result table ↗

    Jingwei Yi, Yueqi Xie, Bin Zhu, Emre Kiciman, Guangzhong Sun, Xing Xie et al. · 2023

    All 7 authors

    Jingwei Yi, Yueqi Xie, Bin Zhu, Emre Kiciman, Guangzhong Sun, Xing Xie, Fangzhao Wu

  3. The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models — published result table ↗

    Li, Junyi, Chen, Jie, Ren, Ruiyang, Cheng, Xiaoxue, Zhao, Wayne Xin, Nie, Jian-Yun et al. · 2024

    All 7 authors

    Li, Junyi, Chen, Jie, Ren, Ruiyang, Cheng, Xiaoxue, Zhao, Wayne Xin, Nie, Jian-Yun, Wen, Ji-Rong

  4. CriticBench: Benchmarking LLMs for Critique-Correct Reasoning — published result table ↗

    Zicheng Lin, Zhibin Gou, Tian Liang, Ruilin Luo, Haowei Liu, Yujiu Yang · 2024

  5. Large Language Models in the Clinic: A Comprehensive Benchmark — published result table ↗

    Liu, Fenglin, Li, Zheng, Zhou, Hongjian, Yin, Qingyu, Yang, Jingfeng, Tang, Xianfeng et al. · 2024

    All 19 authors

    Liu, Fenglin, Li, Zheng, Zhou, Hongjian, Yin, Qingyu, Yang, Jingfeng, Tang, Xianfeng, Luo, Chen, Zeng, Ming, Jiang, Haoming, Gao, Yifan, Nigam, Priyanka, Nag, Sreyashi, Yin, Bing, Hua, Yining, Zhou, Xuan, Rohanian, Omid, Thakur, Anshul, Clifton, Lei, Clifton, David A.

  6. Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation — published result table ↗

    Liu, Jiawei, Xia, Chunqiu Steven, Wang, Yuyao, Zhang, Lingming · 2023

  7. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation — published result table ↗

    Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh et al. · 2023

    All 9 authors

    Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, Hannaneh Hajishirzi

  8. AlpacaEval: An Automatic Evaluator of Instruction-following Models ↗

    Xuechen Li, Tianyi Zhang, Yann Dubois, Rohan Taori, Ishaan Gulrajani, Carlos Guestrin et al. · 2023

    All 8 authors

    Xuechen Li, Tianyi Zhang, Yann Dubois, Rohan Taori, Ishaan Gulrajani, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto

Names used in source tables

Vicuna 13B · Vicuna-13B · Vicuna-13b · vicuna-13b