benchmarks / lmarena-factuality
LMArena Text factuality
Arena score. Status active. Contamination risk low. Maintainer LMArena. Source.
| Model | Score | Date | Kind |
|---|---|---|---|
| Claude Opus 4.6 Thinking | 1492.6689442635038 | 2026-08-11 | snapshot |
| Claude Fable 5 | 1484.03084501396 | 2026-09-13 | snapshot |
| Claude Opus 4.6 | 1489.0563462688256 | 2026-10-08 | snapshot |
| GPT-5.4 | 1484.5604990824759 | 2026-10-08 | snapshot |
| GPT-5.5 | 1486.012226595703 | 2026-10-08 | snapshot |
| Gemini 3 Pro | 1481.2287669363354 | 2026-10-08 | snapshot |
| GPT-5.5 | 1482.1449097441227 | 2026-10-08 | snapshot |
| Qwen3 7 Max Preview | 1480.641896299821 | 2026-09-25 | snapshot |
| Muse Spark 1.1 | 1475.6154011199114 | 2026-07-20 | snapshot |
| Claude Opus 4.7 Thinking | 1476.5384570808687 | 2026-07-30 | snapshot |
| Gemini 3.5 Flash | 1479.3178820715902 | 2026-09-01 | snapshot |
| GPT-5.4 | 1475.943131949057 | 2026-08-03 | snapshot |
| Gemini 3.6 Flash | 1475.0333749745848 | 2026-07-21 | snapshot |
| Claude Opus 5 | 1479.274000645789 | 2026-09-01 | snapshot |
| Claude Opus 5 | 1488.9696662987685 | 2026-10-08 | snapshot |
| Qwen3 8 | 1480.5672936154328 | 2026-08-12 | snapshot |
| Muse Spark 1.2 | 1482.6353124004281 | 2026-10-02 | snapshot |
| Claude Opus 4.6 | 1493.4799900641547 | 2026-10-08 | snapshot |
| Gemini 3.7 Flash | 1485.6768174411613 | 2026-09-13 | snapshot |
| Claude Fable 5.1 | 1498.476253379296 | 2026-10-08 | snapshot |
| Gemini 3.8 Flash | 1489.993080095143 | 2026-09-13 | snapshot |
| Muse Spark 1.3 | 1482.8336515398073 | 2026-09-13 | snapshot |
| Claude Fable 5 | 1483.7803862410397 | 2026-10-08 | snapshot |
| Mimo V2.6 Pro | 1483.8404055983801 | 2026-10-08 | snapshot |
| Gemini 4 Argon | 1511.6498903397928 | 2026-10-08 | snapshot |
| Claude Opus 5.5 | 1509.2033268058926 | 2026-10-08 | snapshot |