RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-4 Turbo

17 benchmarks · 70 observations · 17 sources

Scores at a glance

17 benchmarks · large dot: GPT-4 Turbo; small dots: closest models where reported

MathOdyssey ↗47.03%
19.6455.8

GPT-4 Turbo · MathOdyssey · Overall accuracy · original model comparison ↗

BLINK ↗53.9%
34.695.7

🥉 GPT-4 Turbo · BLINK · Test accuracy · 1,907 test items ↗

AndroidWorld ↗15.5%
15.515.5

GPT-4 Turbo · AndroidWorld · Task success · original comparison ↗

3 more reported results

19.8% · GPT-4 Turbo · AndroidWorld · Task success · original comparison · AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents ↗

30.6% · GPT-4 Turbo · AndroidWorld · Task success · original comparison · AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents ↗

25.4% · GPT-4 Turbo · AndroidWorld · Task success · original comparison · AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents ↗

FinanceBench ↗9%
99

GPT-4-Turbo · FinanceBench · Correct-answer rate · human evaluation · 150-question evaluated sample ↗

4 more reported results

19% · GPT-4-Turbo · FinanceBench · Correct-answer rate · human evaluation · 150-question evaluated sample · FinanceBench: A New Benchmark for Financial Question Answering ↗

50% · GPT-4-Turbo · FinanceBench · Correct-answer rate · human evaluation · 150-question evaluated sample · FinanceBench: A New Benchmark for Financial Question Answering ↗

79% · GPT-4-Turbo · FinanceBench · Correct-answer rate · human evaluation · 150-question evaluated sample · FinanceBench: A New Benchmark for Financial Question Answering ↗

85% · GPT-4-Turbo · FinanceBench · Correct-answer rate · human evaluation · 150-question evaluated sample · FinanceBench: A New Benchmark for Financial Question Answering ↗

τ-Bench ↗57.7%
14.861.2

gpt-4-turbo · τ-Bench · Retail · pass^1 · Original tau-bench · function-calling agents ↗

2 more reported results

32.4% · gpt-4-turbo · τ-Bench · Airline · pass^1 · Original tau-bench · function-calling agents · $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains ↗

45.1% · gpt-4-turbo · τ-Bench · Domain average · pass^1 · Original tau-bench · function-calling agents · $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains ↗

SciBench ↗40.99%
1.0340.99

GPT-4-Turbo · SciBench · Textbook overall accuracy · prompting and tool conditions ↗

3 more reported results

42.37% · GPT-4-Turbo · SciBench · Textbook overall accuracy · prompting and tool conditions · SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models ↗

39.45% · GPT-4-Turbo · SciBench · Textbook overall accuracy · prompting and tool conditions · SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models ↗

28.47% · GPT-4-Turbo · SciBench · Textbook overall accuracy · prompting and tool conditions · SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models ↗

DarkBench ↗48%
3061

GPT-4 Turbo · DarkBench · DarkScore · six-category mean · publisher website comparison ↗

6 more reported results

18% · GPT-4 Turbo · DarkBench · Anthropomorphization · publisher website comparison · DarkBench: Benchmarking Dark Patterns in Large Language Models — publisher leaderboard data ↗

49% · GPT-4 Turbo · DarkBench · Brand bias · publisher website comparison · DarkBench: Benchmarking Dark Patterns in Large Language Models — publisher leaderboard data ↗

69% · GPT-4 Turbo · DarkBench · Harmful generation · publisher website comparison · DarkBench: Benchmarking Dark Patterns in Large Language Models — publisher leaderboard data ↗

69% · GPT-4 Turbo · DarkBench · Sneaking · publisher website comparison · DarkBench: Benchmarking Dark Patterns in Large Language Models — publisher leaderboard data ↗

10% · GPT-4 Turbo · DarkBench · Sycophancy · publisher website comparison · DarkBench: Benchmarking Dark Patterns in Large Language Models — publisher leaderboard data ↗

75% · GPT-4 Turbo · DarkBench · User retention · publisher website comparison · DarkBench: Benchmarking Dark Patterns in Large Language Models — publisher leaderboard data ↗

LAB-Bench (v1) ↗12%
635

gpt-4-turbo · LAB-Bench (v1) · Accuracy · LitQA2 ↗

32 more reported results

6% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SuppQA · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

25% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · FigQA · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

54% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · TableQA · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

4.8% · gpt-4-turbo · LAB-Bench · DbQA · subtask macro average · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

37% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · ProtocolQA · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

28.2667% · gpt-4-turbo · LAB-Bench · SeqQA · subtask macro average · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

9% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · CloningScenarios · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

5% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_dga_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

12% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_gene_location_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

1% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_mirna_targets_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

16% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_mouse_tumor_gene_sets-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

6% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_oncogenic_signatures_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

0% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_tfbs_GTRD_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

0% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_variant_from_sequence_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

0% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_variant_multi_sequence_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

6% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_vax_response_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

2% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · DbQA_viral_ppi_task-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

7% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_ORF-seq-AAid-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

39% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_ORF-seq-AAseq-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

7% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_ORF-seq-numlen-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

29% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_ORF-transeff-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

49% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-gene-enzprimers-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

13% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-gene-gibshindprimers-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

29% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-gene-gibssmaprimers-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

66% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-geneprimers-enz-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

10% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-len-primers-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

19% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-primers-len-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

67% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-seq-enzprimers-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

52% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_PCR-seq-primers-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

18% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_Prop-seq-gcpercent-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

7% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_RE-seq-lenfrags-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

12% · gpt-4-turbo · LAB-Bench (v1) · Accuracy · SeqQA_RE-seq-numfrags-v1 · LAB-Bench: Measuring Capabilities of Language Models for Biology Research ↗

Closest models by score

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

There are not enough shared scored settings to identify close comparisons reliably.

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. SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models — published result table ↗

    Wang, Xiaoxuan, Hu, Ziniu, Lu, Pan, Zhu, Yanqiao, Zhang, Jieyu, Subramaniam, Satyen et al. · 2023

    All 10 authors

    Wang, Xiaoxuan, Hu, Ziniu, Lu, Pan, Zhu, Yanqiao, Zhang, Jieyu, Subramaniam, Satyen, Loomba, Arjun R., Zhang, Shichang, Sun, Yizhou, Wang, Wei

  2. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? — published result table ↗

    Jimenez, Carlos E., Yang, John, Wettig, Alexander, Yao, Shunyu, Pei, Kexin, Press, Ofir et al. · 2023

    All 7 authors

    Jimenez, Carlos E., Yang, John, Wettig, Alexander, Yao, Shunyu, Pei, Kexin, Press, Ofir, Narasimhan, Karthik

  3. FinanceBench: A New Benchmark for Financial Question Answering — published result table ↗

    Islam, Pranab, Kannappan, Anand, Kiela, Douwe, Qian, Rebecca, Scherrer, Nino, Vidgen, Bertie · 2023

  4. GAIA: a benchmark for General AI Assistants — published result table ↗

    Mialon, Grégoire, Fourrier, Clémentine, Swift, Craig, Wolf, Thomas, LeCun, Yann, Scialom, Thomas · 2023

  5. Evaluating Very Long-Term Conversational Memory of LLM Agents — published result table ↗

    Maharana, Adyasha, Lee, Dong-Ho, Tulyakov, Sergey, Bansal, Mohit, Barbieri, Francesco, Fang, Yuwei · 2024

  6. AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents — published result table ↗

    Christopher Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair et al. · 2024

    All 15 authors

    Christopher Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair, Alice Li, William Bishop, Wei Li, Folawiyo Campbell-Ajala, Daniel Toyama, Robert Berry, Divya Tyamagundlu, Timothy Lillicrap, Oriana Riva

  7. MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures — published result table ↗

    Jinjie Ni, Fuzhao Xue, Xiang Yue, Yuntian Deng, Mahir Shah, Kabir Jain et al. · 2024

    All 8 authors

    Jinjie Ni, Fuzhao Xue, Xiang Yue, Yuntian Deng, Mahir Shah, Kabir Jain, Graham Neubig, Yang You

  8. $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains — published result table ↗

    Yao, Shunyu, Shinn, Noah, Razavi, Pedram, Narasimhan, Karthik · 2024

  9. AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents — published result table ↗

    Edoardo Debenedetti, Jie Zhang, Mislav Balunović, Luca Beurer-Kellner, Marc Fischer, Florian Tramèr · 2024

  10. One Thousand and One Pairs: A "novel" challenge for long-context language models — published result table ↗

    Marzena Karpinska, Katherine Thai, Kyle Lo, Tanya Goyal, Mohit Iyyer · 2024

  11. MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data — published result table ↗

    Meng Fang, Xiangpeng Wan, Fei Lu, Fei Xing, Kai Zou · 2024

  12. LAB-Bench: Measuring Capabilities of Language Models for Biology Research — published result table ↗

    Jon M. Laurent, Joseph D. Janizek, Michael Ruzo, Michaela M. Hinks, Michael J. Hammerling, Siddharth Narayanan et al. · 2024

    All 9 authors

    Jon M. Laurent, Joseph D. Janizek, Michael Ruzo, Michaela M. Hinks, Michael J. Hammerling, Siddharth Narayanan, Manvitha Ponnapati, Andrew D. White, Samuel G. Rodriques

  13. LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs — published result table ↗

    Bai, Yushi, Zhang, Jiajie, Lv, Xin, Zheng, Linzhi, Zhu, Siqi, Hou, Lei et al. · 2024

    All 9 authors

    Bai, Yushi, Zhang, Jiajie, Lv, Xin, Zheng, Linzhi, Zhu, Siqi, Hou, Lei, Dong, Yuxiao, Tang, Jie, Li, Juanzi

  14. DarkBench: Benchmarking Dark Patterns in Large Language Models — publisher leaderboard data — published result table ↗

    Esben Kran, Hieu Minh Nguyen, Akash Kundu, Sami Jawhar, Jinsuk Park, Mateusz Maria Jurewicz · 2025

  15. BLINK: Multimodal Large Language Models Can See but Not Perceive — published result table ↗

    Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin et al. · 2024

    All 10 authors

    Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin, Dan Roth, Noah A. Smith, Wei-Chiu Ma, Ranjay Krishna

  16. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  17. MedQA — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

GPT 4 Turbo · GPT-4 Turbo · GPT-4-Turbo · GPT-4-turbo · GPT4 Turbo · gpt-4-turbo · 🥉 GPT-4 Turbo