LLM Benchmarks Timeline: Difference between revisions
No edit summary |
|||
Line 175: | Line 175: | ||
! Original Score | ! Original Score | ||
! Final Score | ! Final Score | ||
! Details | |||
! Links | ! Links | ||
|- | |- | ||
| | | [[BIG-Bench]] | ||
| Multi-task | | Multi-task | ||
| 2021-06 – 2022-04 | | 2021-06 – 2022-04 | ||
Line 187: | Line 187: | ||
| Human: 49.8% | | Human: 49.8% | ||
| Palm 540B: 61.4% | | Palm 540B: 61.4% | ||
| 204 tasks spanning linguistics, math, common-sense reasoning, and more. | |||
| [https://arxiv.org/abs/2206.04615 Paper], [https://github.com/google/BIG-bench GitHub], [https://arxiv.org/pdf/2204.02311 Evidence] | | [https://arxiv.org/abs/2206.04615 Paper], [https://github.com/google/BIG-bench GitHub], [https://arxiv.org/pdf/2204.02311 Evidence] | ||
|} | |} | ||
Line 203: | Line 203: | ||
! Original Score | ! Original Score | ||
! Final Score | ! Final Score | ||
! Details | |||
! Links | ! Links | ||
|- | |- | ||
| | | [[SuperGLUE]] | ||
| Language | | Language | ||
| 2019-05 – 2019-10 | | 2019-05 – 2019-10 | ||
Line 215: | Line 215: | ||
| Human: 89.8% | | Human: 89.8% | ||
| T5: 89.3% | | T5: 89.3% | ||
| More challenging language understanding tasks (word sense, causal reasoning, RC). | | More challenging language understanding tasks (word sense, causal reasoning, RC). | ||
| [https://arxiv.org/abs/1905.00537 Paper], [https://super.gluebenchmark.com/ Website] | |||
|- | |- | ||
| | | [[WSC]] | ||
| Common Sense | | Common Sense | ||
| 2012-05 – 2019-07 | | 2012-05 – 2019-07 | ||
Line 227: | Line 227: | ||
| Human: 96.5% | | Human: 96.5% | ||
| ROBERTA (w SFT): 90.1% | | ROBERTA (w SFT): 90.1% | ||
| Carefully crafted sentence pairs with ambiguous pronoun references. | | Carefully crafted sentence pairs with ambiguous pronoun references. | ||
| [https://cdn.aaai.org/ocs/4492/4492-21843-1-PB.pdf Paper], [https://cs.nyu.edu/~davise/papers/WinogradSchemas/WS.html Website] | |||
|- | |- | ||
| | | [[GLUE]] | ||
| Language | | Language | ||
| 2018-05 – 2019-06 | | 2018-05 – 2019-06 | ||
Line 239: | Line 239: | ||
| Human: 87.1% | | Human: 87.1% | ||
| XLNet: 88.4% | | XLNet: 88.4% | ||
| Nine tasks for evaluating NLU (inference, paraphrase, similarity, etc.). | | Nine tasks for evaluating NLU (inference, paraphrase, similarity, etc.). | ||
| [https://arxiv.org/abs/1804.07461 Paper], [https://gluebenchmark.com/ Website] | |||
|- | |- | ||
| | | [[TriviaQA]] | ||
| Knowledge | | Knowledge | ||
| 2017-05 – 2019-06 | | 2017-05 – 2019-06 | ||
Line 251: | Line 251: | ||
| Human: 79.7% | | Human: 79.7% | ||
| SpanBERT: 83.6% | | SpanBERT: 83.6% | ||
| 650K QA-evidence triples requiring cross-sentence reasoning. | | 650K QA-evidence triples requiring cross-sentence reasoning. | ||
| [https://arxiv.org/abs/1705.03551 Paper], [http://nlp.cs.washington.edu/triviaqa/ Website] | |||
|- | |- | ||
| | | [[SQuAD v2.0]] | ||
| Language | | Language | ||
| 2018-05 – 2019-04 | | 2018-05 – 2019-04 | ||
Line 263: | Line 263: | ||
| Human: 89.5% | | Human: 89.5% | ||
| BERT: 89.5% | | BERT: 89.5% | ||
| Extension of SQuAD adding unanswerable questions. | | Extension of SQuAD adding unanswerable questions. | ||
| [https://arxiv.org/abs/1806.03822 Paper], [https://rajpurkar.github.io/SQuAD-explorer/ Website] | |||
|- | |- | ||
| | | [[SQuAD]] | ||
| Language | | Language | ||
| 2016-05 – 2019-03 | | 2016-05 – 2019-03 | ||
Line 275: | Line 275: | ||
| Human: 91.2% | | Human: 91.2% | ||
| BERT: 93.2% | | BERT: 93.2% | ||
| 100,000+ QA tasks on Wikipedia articles. | | 100,000+ QA tasks on Wikipedia articles. | ||
| [https://arxiv.org/abs/1606.05250 Paper], [https://rajpurkar.github.io/SQuAD-explorer/ Website] | |||
|} | |} | ||
=== 2018 === | === 2018 === | ||
Line 292: | Line 291: | ||
! Original Score | ! Original Score | ||
! Final Score | ! Final Score | ||
! Details | |||
! Links | ! Links | ||
|- | |- | ||
| | | [[SWAG]] | ||
| Common Sense | | Common Sense | ||
| 2018-05 – 2018-10 | | 2018-05 – 2018-10 | ||
Line 304: | Line 303: | ||
| Human: 88% | | Human: 88% | ||
| BERT: 86% | | BERT: 86% | ||
| 113K multiple-choice questions about grounded situations (common sense “next step”). | | 113K multiple-choice questions about grounded situations (common sense “next step”). | ||
| [https://arxiv.org/abs/1808.05326 Paper], [https://rowanzellers.com/swag/ Website] | |||
|} | |} |
Revision as of 16:56, 10 January 2025
2024
Benchmark | Category | Time Span | Date Created | Date Defeated | Killed By | Defeated By | Original Score | Final Score | Details | Links |
---|---|---|---|---|---|---|---|---|---|---|
ARC-AGI | Reasoning | 2019-11 – 2024-12 | 2019-11 | 2024-12 | Saturation | O3 | Human Baseline: ~80% | O3: 87.5% | Abstract reasoning challenge with visual pattern completion tasks created by François Chollet. | Paper, Website |
MATH | Mathematics | 2021-03 – 2024-09 | 2021-03 | 2024-09 | Saturation | O1 | Average CS PhD: ~40% | O1: 94.8% | 12K challenging competition math problems from AMC/AIME, requiring complex multi-step reasoning. | Paper, GitHub |
BIG-Bench-Hard | Multi-task | 2022-10 – 2024-06 | 2022-10 | 2024-06 | Saturation | Sonnet 3.5 | Average Human: 67.7% | Sonnet 3.5: 93.1% | A curated suite of 23 challenging tasks from BIG-Bench. | Paper, GitHub, Evidence |
HumanEval | Coding | 2021-07 – 2024-05 | 2021-07 | 2024-05 | Saturation | GPT-4o | Unspecified | GPT-4o: 90.2% | 164 Python programming problems testing coding abilities. | Paper, GitHub, Evidence |
IFEval | Instruction Following | 2023-11 – 2024-03 | 2023-11 | 2024-03 | Saturation | LLama 3.3 70B | Unspecified | LLama 3.3 70B: 92.1% | Evaluation suite testing multi-step instruction-following capabilities. | Paper, GitHub, Evidence |
2023
Benchmark | Category | Time Span | Date Created | Date Defeated | Killed By | Defeated By | Original Score | Final Score | Details | Links |
---|---|---|---|---|---|---|---|---|---|---|
GSM8K | Mathematics | 2021-10 – 2023-11 | 2021-10 | 2023-11 | Saturation | GPT-4 | Unspecified | GPT-4: 92.0% | 8.5K grade school math word problems requiring step-by-step solutions. | Paper, GitHub, Evidence |
Turing Test | Conversation | 1950-10 – 2023-03 | 1950-10 | 2023-03 | Saturation | GPT-4 | Interrogator > 50% | Interrogator 46% | The original AI benchmark proposed by Alan Turing in 1950 (the "imitation game"). | Paper, Evidence |
ARC (AI2) | Reasoning | 2018-03 – 2023-03 | 2018-03 | 2023-03 | Saturation | GPT-4 | Unspecified | GPT-4: 96.3% | Grade-school multiple-choice reasoning tasks testing logical, spatial, temporal reasoning. | Paper, Website, Evidence |
HellaSwag | Common Sense | 2019-05 – 2023-03 | 2019-05 | 2023-03 | Saturation | GPT-4 | Human: 95.6% | GPT-4: 95.3% | Multiple-choice questions about everyday scenarios with adversarial filtering. | Paper, Website, Evidence |
MMLU | Knowledge | 2020-09 – 2023-03 | 2020-09 | 2023-03 | Saturation | GPT-4 | 95th pct Human: 87.0% | GPT-4: 87.3% | 57 subjects from real-world sources (professional exams) testing breadth and depth of knowledge. | Paper, GitHub, Evidence |
WinoGrande | Common Sense | 2019-07 – 2023-03 | 2019-07 | 2023-03 | Saturation | GPT-4 | Human: 94% | GPT-4: 87.5% | Enhanced WSC with 44K problems testing common-sense pronoun resolution. | Paper, Website, Evidence |
Pre-2023
2022
Benchmark | Category | Time Span | Date Created | Date Defeated | Killed By | Defeated By | Original Score | Final Score | Details | Links |
---|---|---|---|---|---|---|---|---|---|---|
BIG-Bench | Multi-task | 2021-06 – 2022-04 | 2021-06 | 2022-04 | Saturation | Palm 540B | Human: 49.8% | Palm 540B: 61.4% | 204 tasks spanning linguistics, math, common-sense reasoning, and more. | Paper, GitHub, Evidence |
2019
Benchmark | Category | Time Span | Date Created | Date Defeated | Killed By | Defeated By | Original Score | Final Score | Details | Links |
---|---|---|---|---|---|---|---|---|---|---|
SuperGLUE | Language | 2019-05 – 2019-10 | 2019-05 | 2019-10 | Saturation | T5 | Human: 89.8% | T5: 89.3% | More challenging language understanding tasks (word sense, causal reasoning, RC). | Paper, Website |
WSC | Common Sense | 2012-05 – 2019-07 | 2012-05 | 2019-07 | Saturation | ROBERTA (w SFT) | Human: 96.5% | ROBERTA (w SFT): 90.1% | Carefully crafted sentence pairs with ambiguous pronoun references. | Paper, Website |
GLUE | Language | 2018-05 – 2019-06 | 2018-05 | 2019-06 | Saturation | XLNet | Human: 87.1% | XLNet: 88.4% | Nine tasks for evaluating NLU (inference, paraphrase, similarity, etc.). | Paper, Website |
TriviaQA | Knowledge | 2017-05 – 2019-06 | 2017-05 | 2019-06 | Saturation | SpanBERT | Human: 79.7% | SpanBERT: 83.6% | 650K QA-evidence triples requiring cross-sentence reasoning. | Paper, Website |
SQuAD v2.0 | Language | 2018-05 – 2019-04 | 2018-05 | 2019-04 | Saturation | BERT | Human: 89.5% | BERT: 89.5% | Extension of SQuAD adding unanswerable questions. | Paper, Website |
SQuAD | Language | 2016-05 – 2019-03 | 2016-05 | 2019-03 | Saturation | BERT | Human: 91.2% | BERT: 93.2% | 100,000+ QA tasks on Wikipedia articles. | Paper, Website |
2018
Benchmark | Category | Time Span | Date Created | Date Defeated | Killed By | Defeated By | Original Score | Final Score | Details | Links |
---|---|---|---|---|---|---|---|---|---|---|
SWAG | Common Sense | 2018-05 – 2018-10 | 2018-05 | 2018-10 | Saturation | BERT | Human: 88% | BERT: 86% | 113K multiple-choice questions about grounded situations (common sense “next step”). | Paper, Website |