Difference between revisions of "AI benchmarks"
KevinYager (talk | contribs) (→Reasoning) |
KevinYager (talk | contribs) (→Assess Specific Attributes) |
||
| (4 intermediate revisions by the same user not shown) | |||
| Line 30: | Line 30: | ||
==Software/Coding== | ==Software/Coding== | ||
* 2025-02: [https://arxiv.org/abs/2502.12115SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?] ([https://github.com/openai/SWELancer-Benchmark code]) | * 2025-02: [https://arxiv.org/abs/2502.12115SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?] ([https://github.com/openai/SWELancer-Benchmark code]) | ||
| + | |||
| + | ==Math== | ||
| + | * [https://www.vals.ai/benchmarks/aime-2025-03-13 AIME Benchmark] | ||
==Visual== | ==Visual== | ||
| + | * 2024-06: [https://charxiv.github.io/ Charting Gaps in Realistic Chart Understanding in Multimodal LLMs] ([https://arxiv.org/abs/2406.18521 preprint], [https://charxiv.github.io/ leaderboard]) | ||
* 2025-03: [https://arxiv.org/abs/2503.14607 Can Large Vision Language Models Read Maps Like a Human?] MapBench | * 2025-03: [https://arxiv.org/abs/2503.14607 Can Large Vision Language Models Read Maps Like a Human?] MapBench | ||
| + | |||
| + | ==Conversation== | ||
| + | * 2025-01: [https://arxiv.org/abs/2501.17399 MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs] ([https://scale.com/research/multichallenge project], [https://github.com/ekwinox117/multi-challenge code], [https://scale.com/leaderboard/multichallenge leaderboard]) | ||
==Creativity== | ==Creativity== | ||
| Line 46: | Line 53: | ||
==Assistant/Agentic== | ==Assistant/Agentic== | ||
| + | See: [[AI_Agents#Optimization|AI Agents: Optimization]] | ||
* [https://arxiv.org/abs/2311.12983 GAIA: a benchmark for General AI Assistants] | * [https://arxiv.org/abs/2311.12983 GAIA: a benchmark for General AI Assistants] | ||
* [https://www.galileo.ai/blog/agent-leaderboard Galileo AI] [https://huggingface.co/spaces/galileo-ai/agent-leaderboard Agent Leaderboard] | * [https://www.galileo.ai/blog/agent-leaderboard Galileo AI] [https://huggingface.co/spaces/galileo-ai/agent-leaderboard Agent Leaderboard] | ||
Latest revision as of 13:39, 16 April 2025
Contents
General
- Models Table (lifearchitect.ai)
- Artificial Analysis
- Epoch AI
Methods
- AidanBench: Evaluating Novel Idea Generation on Open-Ended Questions (code)
- Leaderboard
- Suggestion to use Borda count
- 2025-04: add Quasar Alpha, Optimus Alpha, Llama-4 Scout and Llama-4 Maverick
- ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning. Assess reasoning using puzzles of tunable complexity.
Task Length
- 2020-09: Ajeya Cotra: Draft report on AI timelines
- 2025-03: Measuring AI Ability to Complete Long Tasks Measuring AI Ability to Complete Long Tasks
Assess Specific Attributes
Various
- LMSYS: Human preference ranking leaderboard
- Tracking AI: "IQ" leaderboard
- LiveBench: A Challenging, Contamination-Free LLM Benchmark
- LLM Thematic Generalization Benchmark
Hallucination
Software/Coding
Math
Visual
- 2024-06: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs (preprint, leaderboard)
- 2025-03: Can Large Vision Language Models Read Maps Like a Human? MapBench
Conversation
- 2025-01: MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs (project, code, leaderboard)
Creativity
- 2024-10: AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
- 2024-11: AidanBench: Evaluating Novel Idea Generation on Open-Ended Questions (code)
- 2024-12: LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context
- LLM Creative Story-Writing Benchmark
Reasoning
- ENIGMAEVAL: "reasoning" leaderboard (paper)
- Sober Reasoning Leaderboard
Assistant/Agentic
- GAIA: a benchmark for General AI Assistants
- Galileo AI Agent Leaderboard
- Smolagents LLM Leaderboard: LLMs powering agents
- OpenAI PaperBench: Evaluating AI’s Ability to Replicate AI Research (paper, code)
Science
See: Science Benchmarks
