AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
LiveBench
LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Abacus.AI
- Benchmark release
- 2024-06-12
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 38
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| o3-mini | 0.846 | Not recorded | Not recorded | 2025-01-30 · model_announcement | LLM Stats |
| GPT-5.5 | 0.8071 | Not recorded | Not recorded | 2026-04-23 · model_announcement | LLM Stats |
| GPT-5.4 | 0.8028 | Not recorded | Not recorded | 2026-03-05 · model_announcement | LLM Stats |
| Gemini 3.1 Pro | 0.7993 | Not recorded | Not recorded | 2026-02-19 · model_announcement | LLM Stats |
| Claude Fable 5 | 0.7831 | Not recorded | Not recorded | 2026-06-09 · model_announcement | LLM Stats |
| Claude Opus 4.8 | 0.7722 | Not recorded | Not recorded | 2026-05-28 · model_announcement | LLM Stats |
| Qwen3 235B A22B | 0.771 | Not recorded | Not recorded | 2025-04-29 · model_announcement | LLM Stats |
| Claude Opus 4.7 | 0.7691 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| Kimi K2-Instruct-0905 | 0.764 | Not recorded | Not recorded | 2025-09-05 · model_announcement | LLM Stats |
| Kimi K2 Instruct | 0.764 | Not recorded | Not recorded | 2025-07-11 · model_announcement | LLM Stats |
| Claude Opus 4.6 | 0.7633 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| Claude Opus 4.5 | 0.7596 | Not recorded | Not recorded | 2025-11-24 · model_announcement | LLM Stats |
| Claude Sonnet 4.6 | 0.7547 | Not recorded | Not recorded | 2026-02-17 · model_announcement | LLM Stats |
| Gemini 3.5 Flash | 0.7502 | Not recorded | Not recorded | 2026-05-19 · model_announcement | LLM Stats |
| Qwen3 32B | 0.749 | Not recorded | Not recorded | 2025-04-29 · model_announcement | LLM Stats |
| GPT-5.2 | 0.7484 | Not recorded | Not recorded | 2025-12-11 · model_announcement | LLM Stats |
| GPT-5.2 Codex | 0.743 | Not recorded | Not recorded | 2026-01-14 · model_announcement | LLM Stats |
| Qwen3 30B A3B | 0.743 | Not recorded | Not recorded | 2025-04-29 · model_announcement | LLM Stats |
| Qwen3.7 Max | 0.7429 | Not recorded | Not recorded | 2026-05-19 · model_announcement | LLM Stats |
| DeepSeek-V4-Pro-Max | 0.7358 | Not recorded | Not recorded | 2026-04-23 · model_announcement | LLM Stats |
| Gemini 3 Pro | 0.7339 | Not recorded | Not recorded | 2025-11-18 · model_announcement | LLM Stats |
| QwQ-32B | 0.731 | Not recorded | Not recorded | 2025-03-05 · model_announcement | LLM Stats |
| GPT-5.3 Codex | 0.7276 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| Gemini 3 Flash | 0.724 | Not recorded | Not recorded | 2025-12-17 · model_announcement | LLM Stats |
| Kimi K2.6 | 0.7217 | Not recorded | Not recorded | 2026-04-20 · model_announcement | LLM Stats |
| GPT-5.1 High | 0.7204 | Not recorded | Not recorded | 2025-11-12 · model_announcement | LLM Stats |
| Kimi K2.7 Code | 0.7189 | Not recorded | Not recorded | 2026-06-12 · model_announcement | LLM Stats |
| Qwen3.6 Plus | 0.7085 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| GLM-5.1 | 0.7018 | Not recorded | Not recorded | 2026-04-07 · model_announcement | LLM Stats |
| GPT-5.4 nano | 0.7013 | Not recorded | Not recorded | 2026-03-17 · model_announcement | LLM Stats |
| MiniMax M3 | 0.7002 | Not recorded | Not recorded | 2026-06-01 · model_announcement | LLM Stats |
| Kimi K2.5 | 0.6907 | Not recorded | Not recorded | 2026-01-27 · model_announcement | LLM Stats |
| o1 | 0.67 | Not recorded | Not recorded | 2024-12-17 · model_announcement | LLM Stats |
| Qwen2.5 72B Instruct | 0.523 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| o1-preview | 0.523 | Not recorded | Not recorded | 2024-09-12 · model_announcement | LLM Stats |
| Phi 4 | 0.476 | Not recorded | Not recorded | 2024-12-12 · model_announcement | LLM Stats |
| Qwen2.5 7B Instruct | 0.359 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Qwen2.5-Omni-7B | 0.296 | Not recorded | Not recorded | 2025-03-27 · model_announcement | LLM Stats |