math benchmark
LiveBench 20241125
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.
Updated Aug 7, 2026
Published models14
Registry coverage14
MetricScore
EvidenceB
LiveBench 20241125 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 79.6% | 100.0% | 14 | C | |
| 2 | AC | 78.4% | 92.3% | 14 | C | |
| 3 | AC | 76.6% | 84.6% | 14 | C | |
| 4 | AC | 75.8% | 76.9% | 14 | C | |
| 5 | AC | 75.4% | 69.2% | 14 | C | |
| 6 | AC | 74.8% | 61.5% | 14 | C | |
| 7 | AC | 74.7% | 53.9% | 14 | C | |
| 8 | AC | 72.2% | 46.1% | 14 | C | |
| 9 | AC | 72.1% | 38.5% | 14 | C | |
| 10 | AC | 69.8% | 30.8% | 14 | C | |
| 11 | AC | 68.4% | 23.1% | 14 | C | |
| 12 | AC | 65.4% | 15.4% | 14 | C | |
| 13 | AC | 62.0% | 7.7% | 14 | C | |
| 14 | AC | 60.9% | 0.0% | 14 | C |
Score distribution
Top published rows on the benchmark's original scale.
LiveBench 20241125 highlights
The top published results on this benchmark's own scale.
What is LiveBench 20241125?
Definition and scoring fields from the benchmark registry.
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.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- LiveBench 20241125
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- livebench-20241125|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about LiveBench 20241125.
Which model scores highest on LiveBench 20241125?
Qwen3 VL 235B A22B Thinking is currently ranked first with 79.6%.
What does LiveBench 20241125 measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
14 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.