---
title: "Overall leaderboard"
description: "Overall rankings of text models across math, coding, creative writing and other open-ended tasks."
canonical: https://pirouter.ai/rankings/overall
last-updated: 2026-10-15
---

# Overall leaderboard

> Overall rankings of text models across math, coding, creative writing and other open-ended tasks.

- Updated: 2026-09-30
- 11,176,540 votes · 385 models
- Score · higher is better

## Full ranking

| Rank | Rank spread | Model | Vendor | Score | Votes |
|---|---|---|---|---|---|
| 1 | 1–1 | Gemini 4 Argon (high) | Google | 1525 ±9 | 4942 |
| 2 | 2–7 | Claude Opus 4.6 (high) | Anthropic | 1506 ±3 | 77193 |
| 3 | 2–8 | Claude Fable 5 (high) | Anthropic | 1505 ±4 | 37900 |
| 4 | 2–12 | [Claude Opus 5.5 \(high\)](https://pirouter.ai/models/anthropic/claude-opus-5.5) | Anthropic | 1504 ±10 | 3932 |
| 5 | 2–9 | Claude Opus 4.7 (high) | Anthropic | 1502 ±4 | 64607 |
| 6 | 2–12 | [Claude Fable 5.1 \(max\)](https://pirouter.ai/models/anthropic/claude-fable-5.1) | Anthropic | 1501 ±7 | 11241 |
| 7 | 3–17 | Muse Spark 1.3 (max) | Meta | 1495 ±6 | 11698 |
| 8 | 2–23 | Muse Spark 1.2 (xhigh) | Meta | 1494 ±10 | 3833 |
| 9 | 4–17 | [Gemini 3.8 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.8-flash) | Google | 1494 ±5 | 24828 |
| 10 | 5–19 | Muse Spark 1.1 | Meta | 1492 ±4 | 36558 |
| 11 | 5–19 | Claude Opus 5 (high) | Anthropic | 1491 ±4 | 58380 |
| 12 | 5–24 | Muse Spark | Meta | 1489 ±6 | 14128 |
| 13 | 7–25 | [Gemini 3.7 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.7-flash) | Google | 1488 ±5 | 20851 |
| 14 | 7–24 | Kimi K3 (max) | Moonshot | 1488 ±5 | 27719 |
| 15 | 7–24 | Gemini 3.1 Pro Preview | Google | 1487 ±3 | 121225 |
| 16 | 7–25 | Gemini 3 Pro | Google | 1486 ±4 | 41910 |
| 17 | 9–29 | [GPT-5.6 Sol \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-sol) | OpenAI | 1484 ±4 | 36002 |
| 18 | 9–32 | [Gemini 3.6 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.6-flash) | Google | 1483 ±4 | 35640 |
| 19 | 11–33 | [GPT-5.5 \(high\)](https://pirouter.ai/models/openai/gpt-5.5) | OpenAI | 1481 ±4 | 69312 |
| 20 | 11–34 | Claude Opus 4.8 (high) | Anthropic | 1481 ±4 | 63577 |
| 21 | 11–36 | Qwen3.8 (max) | Alibaba | 1481 ±5 | 22809 |
| 22 | 7–42 | MiMo V2.6 Pro | Xiaomi | 1480 ±9 | 4074 |
| 23 | 11–38 | GLM 5.3 (max) | Z.ai | 1479 ±6 | 17268 |
| 24 | 17–38 | [Gemini 3.5 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.5-flash) | Google | 1477 ±4 | 47981 |
| 25 | 15–45 | [GPT-6 Astra \(max\)](https://pirouter.ai/models/openai/gpt-6-astra) | OpenAI | 1476 ±7 | 8565 |
| 26 | 17–40 | GPT-5.2 Chat Latest | OpenAI | 1476 ±4 | 35943 |
| 27 | 17–40 | [GLM 5.2 \(max\)](https://pirouter.ai/models/z-ai/glm-5.2) | Z.ai | 1475 ±4 | 44949 |
| 28 | 18–40 | [GPT-5.4 \(high\)](https://pirouter.ai/models/openai/gpt-5.4) | OpenAI | 1475 ±4 | 64648 |
| 29 | 18–43 | Grok 4.20 Beta1 | xAI | 1475 ±5 | 27840 |
| 30 | 12–50 | Qwen3.7 Preview (max) | Alibaba | 1475 ±10 | 3924 |
| 31 | 20–43 | Claude Opus 4.5 20251101 High 32k | Anthropic | 1474 ±4 | 37446 |
| 32 | 18–46 | [GLM 5.3 Flash](https://pirouter.ai/models/z-ai/glm-5.3-flash) | Z.ai | 1474 ±5 | 21644 |
| 33 | 19–48 | GPT-5.5 Instant | OpenAI | 1473 ±5 | 27101 |
| 34 | 17–49 | [DeepSeek V4.1 Flash \(max\)](https://pirouter.ai/models/deepseek/deepseek-v4.1-flash) | DeepSeek | 1473 ±7 | 8125 |
| 35 | 21–46 | Gemini 3 Flash | Google | 1473 ±4 | 31255 |
| 36 | 21–45 | Claude Sonnet 4.6 | Anthropic | 1472 ±4 | 70828 |
| 37 | 22–48 | Grok 4.20 Beta 0309 Reasoning | xAI | 1472 ±4 | 66372 |
| 38 | 22–48 | Grok 4.20 Multi Agent Beta 0309 | xAI | 1471 ±4 | 64838 |
| 39 | 24–48 | Claude Opus 4.5 | Anthropic | 1470 ±3 | 72799 |
| 40 | 24–51 | Ernie 5.1 | Baidu | 1468 ±5 | 39421 |
| 41 | 27–51 | MiMo V2.5 Pro | Xiaomi | 1467 ±4 | 70317 |
| 42 | 28–54 | Grok 4.5 | xAI | 1466 ±4 | 39339 |
| 43 | 32–52 | Grok 4.1 (thinking) | xAI | 1465 ±3 | 66373 |
| 44 | 30–55 | [GPT-5.6 Terra \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-terra) | OpenAI | 1465 ±4 | 37056 |
| 45 | 30–57 | Qwen3.5 Preview (max) | Alibaba | 1465 ±5 | 22566 |
| 46 | 34–55 | GLM 5.1 | Z.ai | 1465 ±4 | 57877 |
| 47 | 27–64 | [DeepSeek V4 Pro 0813 \(high\)](https://pirouter.ai/models/deepseek/deepseek-v4-pro) | DeepSeek | 1464 ±7 | 9825 |
| 48 | 38–64 | [Claude Sonnet 5 \(high\)](https://pirouter.ai/models/anthropic/claude-sonnet-5) | Anthropic | 1462 ±4 | 45191 |
| 49 | 39–64 | Kimi K2.6 | Moonshot | 1461 ±4 | 39950 |
| 50 | 34–69 | Qwen3.6 Preview (max) | Alibaba | 1460 ±8 | 5408 |
| 51 | 44–65 | Gemini 3 Flash | Google | 1458 ±3 | 90888 |
| 52 | 43–67 | GLM 5 | Z.ai | 1458 ±4 | 29203 |
| 53 | 40–70 | Hy3 | Tencent | 1457 ±7 | 10239 |
| 54 | 47–66 | Claude Sonnet 4.5 20250929 High 32k | Anthropic | 1457 ±3 | 83682 |
| 55 | 47–68 | Dola Seed 2.0 Pro | ByteDance | 1457 ±3 | 78956 |
| 56 | 46–69 | Qwen3.7 Plus | Alibaba | 1456 ±4 | 42001 |
| 57 | 42–74 | [GPT-6 Sol \(max\)](https://pirouter.ai/models/openai/gpt-6-sol) | OpenAI | 1456 ±7 | 7574 |
| 58 | 47–69 | GPT-5.1 (high) | OpenAI | 1456 ±4 | 41568 |
| 59 | 47–69 | Claude Sonnet 4.5 | Anthropic | 1455 ±3 | 82438 |
| 60 | 47–74 | [Gemini 3.5 Flash Lite](https://pirouter.ai/models/google/gemini-3.5-flash-lite) | Google | 1454 ±5 | 35335 |
| 61 | 43–79 | MiMo V2.6 Flash | Xiaomi | 1454 ±8 | 5465 |
| 62 | 47–74 | [GPT-5.6 Luna \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-luna) | OpenAI | 1453 ±4 | 37593 |
| 63 | 47–74 | Grok 4.6 (high) | xAI | 1453 ±5 | 23012 |
| 64 | 46–79 | Gemma 4 31b | Google | 1453 ±7 | 6137 |
| 65 | 52–77 | Kimi K2.5 (thinking) | Moonshot | 1450 ±3 | 74623 |
| 66 | 51–78 | GPT-5.3 Chat Latest | OpenAI | 1450 ±4 | 34303 |
| 67 | 53–77 | Claude Opus 4.1 (thinking) | Anthropic | 1450 ±3 | 49334 |
| 68 | 50–85 | Ernie 5.0 Preview 1203 | Baidu | 1449 ±7 | 9788 |
| 69 | 54–84 | MiMo V2 Pro | Xiaomi | 1448 ±5 | 25397 |
| 70 | 59–84 | [GPT-5.4 Mini \(high\)](https://pirouter.ai/models/openai/gpt-5.4-mini) | OpenAI | 1447 ±4 | 63311 |
| 71 | 59–84 | Ernie 5.0 0110 | Baidu | 1447 ±4 | 36422 |
| 72 | 63–84 | Gemini 2.5 Pro | Google | 1446 ±2 | 124859 |
| 73 | 59–88 | GPT-4.5 Preview 2025 02 27 | OpenAI | 1445 ±6 | 14547 |
| 74 | 58–92 | [GPT-6 Luna \(max\)](https://pirouter.ai/models/openai/gpt-6-luna) | OpenAI | 1444 ±7 | 7654 |
| 75 | 63–88 | Qwen3.6 Plus | Alibaba | 1443 ±4 | 48092 |
| 76 | 66–88 | Chatgpt 4o Latest | OpenAI | 1443 ±3 | 81601 |
| 77 | 59–97 | Grok 4.7 (xhigh) | xAI | 1443 ±8 | 5675 |
| 78 | 65–91 | Inkling | Thinky | 1442 ±5 | 34594 |
| 79 | 68–90 | Qwen3.5 397b A17b | Alibaba | 1442 ±3 | 88092 |
| 80 | 63–95 | GLM 4.7 | Z.ai | 1442 ±6 | 12219 |
| 81 | 68–91 | Grok 4.3 | xAI | 1442 ±4 | 71269 |
| 82 | 68–95 | Minimax M3 | MiniMax | 1440 ±4 | 58171 |
| 83 | 68–101 | Qwen3.8 27b | Alibaba | 1439 ±5 | 17777 |
| 84 | 72–97 | [DeepSeek V4 Flash 0731 \(high\)](https://pirouter.ai/models/deepseek/deepseek-v4-flash) | DeepSeek | 1439 ±4 | 51691 |
| 85 | 68–104 | Gemma 4 26b A4b | Google | 1438 ±7 | 6083 |
| 86 | 73–97 | GPT-5.2 (high) | OpenAI | 1437 ±4 | 49549 |
| 87 | 73–101 | Longcat Flash Chat 2602 Exp | Meituan | 1437 ±5 | 29235 |
| 88 | 76–104 | GPT-5 (high) | OpenAI | 1434 ±5 | 31487 |
| 89 | 76–104 | Qwen3 Preview (max) | Alibaba | 1434 ±5 | 27239 |
| 90 | 73–107 | GLM 5v Turbo | Z.ai | 1434 ±6 | 10448 |
| 91 | 77–104 | MiMo V2.5 | Xiaomi | 1434 ±4 | 47292 |
| 92 | 80–105 | Gemini 3.1 Flash Lite Preview | Google | 1433 ±4 | 64094 |
| 93 | 82–107 | O3 2025 04 16 | OpenAI | 1432 ±4 | 58598 |
| 94 | 80–111 | MiMo V2 Omni | Xiaomi | 1431 ±6 | 20611 |
| 95 | 79–113 | Kimi K2.5 Instant | Moonshot | 1431 ±7 | 8355 |
| 96 | 85–109 | Grok 4.1 Fast Reasoning | xAI | 1430 ±3 | 57425 |
| 97 | 85–110 | Kimi K2 Thinking Turbo | Moonshot | 1430 ±3 | 63225 |
| 98 | 85–116 | Mistral Medium 3.5 | Mistral | 1427 ±6 | 11757 |
| 99 | 87–116 | GPT-5 Chat | OpenAI | 1427 ±4 | 31017 |
| 100 | 80–120 | Amazon Nova Experimental Chat 26 02 10 | Amazon | 1427 ±10 | 3519 |

## FAQ

### What is the best AI model for overall?

As of 2026-09-30, Google Gemini 4 Argon (high) is #1 on the overall board with a score of 1525, rank spread 1–1.

### What is the best open-weights model for overall?

Kimi K3 (Moonshot), #14 on this board.

### What does this board rank?

Overall rankings of text models across math, coding, creative writing and other open-ended tasks.

### How often is it updated?

Whenever new models ship or the rankings change; this board was last updated on 2026-09-30.

Data: [LMArena leaderboard dataset](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset), used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); filtered and reasoning tiers merged, scores unchanged.
View the original board: https://arena.ai/leaderboard/text