Best LLM for chat
- Gemini 4 Argon leads
- 1532
- models ranked
- 156
- lead over #2
- +16 Elo
LMArena Text · read October 21
As of October 21, 2026, Google Gemini 4 Argon leads 156 models on LMArena Text with 1532, ahead of Anthropic Claude Opus 5.5 (1516) and Anthropic Claude Fable 5.1 (1512).
This list narrows the best LLM for general use ranking.
| Rank | Model | LMArena Text | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Gemini 4 Argon Google | 1532 | 80.5 | $10.00 | |
| 2 | Claude Opus 5.5 Anthropic | 1516 | 92.2 | $20.00 | |
| 3 | Claude Fable 5.1 Anthropic | 1512 | 89.1 | $50.00 | |
| 4 | Claude Opus 5 Anthropic | 1509 | 81.8 | $25.00 | |
| 5 | Muse Wonder Meta | 1502 | 64.5 | $20.00 | |
| 6 | Claude Opus 4.6 Anthropic | 1501 | 66.9 | $25.00 | |
| 7 | Gemini 3.8 Flash Google | 1499 | 70.5 | $4.125 | |
| 8 | Claude Fable 5 Anthropic | 1491 | 82.1 | $50.00 | |
| 9 | MiMo-V2.6-Pro Xiaomi | 1491 | 72.6 | $0.87 | |
| 10 | Muse Spark 1.3 Meta | 1490 | 79.7 | $4.25 | |
| 11 | Claude Opus 4.7 Anthropic | 1490 | 51.1 | $25.00 | |
| 12 | Gemini 3.7 Flash Google | 1489 | 69.9 | $3.75 | |
| 13 | Qwen3.8 Max (0902) Qwen | 1483 | 63.5 | $6.00 | |
| 14 | Muse Spark 1.2 Meta | 1482 | 65.1 | $4.25 | |
| 15 | Gemini 3.5 Flash Google | 1482 | 42.8 | $9.00 | |
| 16 | Gemini 3.1 Pro Preview Google | 1480 | 35.3 | $12.00 | |
| 17 | Gemini 3.6 Flash Google | 1480 | 48.3 | $3.75 | |
| 18 | Muse Spark 1.1 Meta | 1478 | 48.9 | $4.25 | |
| 19 | Kimi K3 Moonshot AI | 1476 | 61.8 | $11.936 | |
| 20 | GLM 5.3 Z.ai | 1474 | 73.1 | $1.40 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models by their LMArena Text result, as the board publishes it, best first. Every text prompt in the arena. People ask a question, compare two anonymous answers and vote for the better one; the rating is built from those votes, as LMArena publishes it.
- OpenRouter, fetched
- LMArena (Hugging Face dataset), fetched