How to read this table
- Higher rows are rated higher. A range like “1–2” means the gap is within the margin of error.
- The rating comes from people comparing two answers and picking the better one.
- At a gap of 50, the higher model is picked about 57% of the time; 100 means 64%, 200 means 76%.
- Prices are a guide per million tokens, reading then writing.
- Length is how much text the model can read at once (tokens).
± range of the top model
| Rank | Model | Developer | rating | Week change | Overall | Input $ /1M | Output $ /1M | Context | Supports | Weights | Released | Price and specs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1–47 | Claude Fable 5.1 | Anthropic | Rating 1518 ±36 | +8 | 1503rank 2–10 | $10 | $50 | 1M | Anthropic Released 2026-09 Week change +8 Price $10 / $50 Length 1M | |||
| 1–67 | Gemini 4 Argon | Rating 1516 ±49 | New | 1517rank 1–3 | $2 | $10 | 1.05M | Google Released 2026-09 Price $2 / $10 Length 1.05M | ||||
| 1–40 | Claude Fable 5 | Anthropic | Rating 1510 ±22 | −5 | 1503rank 2–9 | $10 | $50 | 1M | Anthropic Released 2026-06 Week change −5 Price $10 / $50 Length 1M | |||
| 1–43 | Muse Spark 1.1 | Meta | Rating 1509 ±23 | +1 | 1490rank 8–23 | $1.25 | $4.25 | 1M | Meta Released 2026-07 Week change +1 Price $1.25 / $4.25 Length 1M | |||
| 1–44 | Gemini 3.5 Flash | Rating 1506 ±22 | 0 | 1477rank 18–41 | $1.5 | $9 | 1.05M | Google Released 2026-05 Price $1.5 / $9 Length 1.05M | ||||
| 1–40 | Gemini 3 Pro | Rating 1505 ±17 | 0 | 1486rank 10–29 | — | — | 1.05M | Google Released 2025-11 Price — Length 1.05M | ||||
| 1–44 | Claude Opus 5 | Anthropic | Rating 1504 ±19 | 0 | 1491rank 8–22 | $5 | $25 | 1M | Anthropic Released 2026-07 Price $5 / $25 Length 1M | |||
| 1–42 | Claude Opus 4.6 | Anthropic | Rating 1502 ±15 | 0 | 1503rank 2–9 | $5 | $25 | 1M | Anthropic Released 2026-02 Price $5 / $25 Length 1M | |||
| 1–45 | Claude Opus 4.7 | Anthropic | Rating 1501 ±18 | +1 | 1501rank 2–10 | $5 | $25 | 1M | Anthropic Released 2026-04 Week change +1 Price $5 / $25 Length 1M | |||
| 1–59 | Gemini 3.7 Flash | Rating 1499 ±27 | −3 | 1490rank 8–25 | $0.75 | $3.75 | 1.05M | Google Released 2026-08 Week change −3 Price $0.75 / $3.75 Length 1.05M | ||||
| 1–54 | Gemini 3 Flash | Rating 1497 ±19 | 0 | 1473rank 23–49 | — | — | 1.05M | Google Released 2025-12 Price — Length 1.05M | ||||
| 1–59 | GPT-5.6 Sol | OpenAI | Rating 1496 ±23 | −7 | 1485rank 10–30 | $4 | $20 | 1.05M | OpenAI Released 2026-07 Week change −7 Price $4 / $20 Length 1.05M | |||
| 1–47 | Gemini 3.1 Pro (preview) | Rating 1495 ±12 | −1 | 1487rank 10–26 | $2 | $12 | 1.05M | Google Released 2026-02 Week change −1 Price $2 / $12 Length 1.05M | ||||
| 1–64 | Gemini 3.8 Flash | Rating 1493 ±24 | −1 | 1496rank 4–15 | $0.75 | $3.75 | 1.05M | Google Released 2026-09 Week change −1 Price $0.75 / $3.75 Length 1.05M | ||||
| 1–60 | Dola Seed 2.0 Pro | ByteDance | Rating 1487 ±16 | 0 | 1456rank 48–71 | — | — | 131.1K | — | ByteDance Released — Price — Length 131.1K | ||
| 1–59 | Grok 4.1 | xAI | Rating 1486 ±14 | 0 | 1465rank 38–53 | — | — | 200K | xAI Released 2025-11 Price — Length 200K | |||
| 1–67 | Claude Opus 4.8 | Anthropic | Rating 1485 ±18 | 0 | 1481rank 12–36 | $5 | $25 | 1M | Anthropic Released 2026-05 Price $5 / $25 Length 1M | |||
| 1–91 | Muse Spark 1.3 | Meta | Rating 1485 ±35 | +1 | 1496rank 3–15 | $1.25 | $4.25 | 1.05M | Meta Released 2026-09 Week change +1 Price $1.25 / $4.25 Length 1.05M | |||
| 1–87 | ERNIE 5.0 (preview, 1203) | Baidu | Rating 1485 ±30 | 0 | 1449rank 52–88 | — | — | — | — | Baidu Released — Price — Length — | ||
| 1–89 | Muse Spark | Meta | Rating 1484 ±33 | 0 | 1489rank 8–27 | — | — | — | Meta Released 2026-04 Price — Length — | |||
| 1–67 | GPT-5.4 | OpenAI | Rating 1482 ±17 | 0 | 1475rank 19–42 | $2.5 | $15 | 1.05M | OpenAI Released 2026-03 Price $2.5 / $15 Length 1.05M | |||
| 1–86 | GPT-5.5 Instant | OpenAI | Rating 1480 ±25 | 0 | 1473rank 20–50 | — | — | — | OpenAI Released 2026-05 Price — Length — | |||
| 1–77 | GPT-5.5 | OpenAI | Rating 1480 ±18 | +1 | 1482rank 12–36 | $5 | $30 | 1.05M | OpenAI Released 2026-04 Week change +1 Price $5 / $30 Length 1.05M | |||
| 1–74 | Grok 4.20 Multi Agent (beta, 0309) | xAI | Rating 1480 ±16 | 0 | 1471rank 24–50 | — | — | — | — | xAI Released — Price — Length — | ||
| 1–87 | GPT-5.2 Chat | OpenAI | Rating 1476 ±22 | 0 | 1476rank 19–42 | — | — | 128K | OpenAI Released 2026-02 Price — Length 128K | |||
| 1–85 | Claude Opus 4.5 | Anthropic | Rating 1476 ±18 | 0 | 1474rank 23–46 | $5 | $25 | 200K | Anthropic Released 2025-11 Price $5 / $25 Length 200K | |||
| 1–92 | GLM-5.3 | Z.ai | Rating 1476 ±30 | −7 | 1481rank 11–38 | $1.4 | $4.4 | 1M | Z.ai Released 2026-08 Week change −7 Price $1.4 / $4.4 Length 1M | |||
| 1–89 | Kimi K3 | Moonshot | Rating 1475 ±24 | −2 | 1487rank 8–27 | $3 | $15 | 1.05M | Moonshot Released 2026-07 Week change −2 Price $3 / $15 Length 1.05M | |||
| 1–88 | GPT-5.3 Chat | OpenAI | Rating 1475 ±22 | 0 | 1450rank 52–80 | — | — | 128K | — | OpenAI Released — Price — Length 128K | ||
| 1–85 | Grok 4.20 Beta Reasoning (0309) | xAI | Rating 1474 ±17 | 0 | 1472rank 24–50 | — | — | 2M | — | xAI Released — Price — Length 2M | ||
| 1–92 | Qwen3.8 Max | Alibaba | Rating 1473 ±27 | −1 | 1483rank 10–36 | $2 | $6 | 1M | Alibaba Released 2026-08 Week change −1 Price $2 / $6 Length 1M | |||
| 1–91 | Gemini 3.6 Flash | Rating 1473 ±25 | 0 | 1483rank 10–35 | $0.75 | $3.75 | 1.05M | Google Released 2026-07 Price $0.75 / $3.75 Length 1.05M | ||||
| 1–103 | Grok 4.7 | xAI | Rating 1473 ±40 | New | 1441rank 65–102 | $2 | $6 | 500K | xAI Released 2026-09 Price $2 / $6 Length 500K | |||
| 1–102 | DeepSeek-V4.1 Flash | DeepSeek | Rating 1472 ±38 | +8 | 1476rank 17–46 | — | — | 1M | DeepSeek Released 2026-09 Week change +8 Price — Length 1M | |||
| 3–86 | Claude Sonnet 4.6 | Anthropic | Rating 1471 ±16 | 0 | 1472rank 24–49 | $3 | $15 | 1M | Anthropic Released 2026-02 Price $3 / $15 Length 1M | |||
| 1–93 | Grok 4.20 (beta1) | xAI | Rating 1468 ±24 | 0 | 1475rank 19–45 | — | — | — | — | xAI Released — Price — Length — | ||
| 8–91 | MiMo-V2.5 Pro | Xiaomi | Rating 1467 ±16 | −2 | 1466rank 34–53 | $0.435 | $0.87 | 1.05M | Xiaomi Released 2026-04 Week change −2 Price $0.435 / $0.87 Length 1.05M | |||
| 8–91 | DeepSeek-V4 Pro | DeepSeek | Rating 1465 ±18 | −1 | 1458rank 47–69 | $0.66 | $1.98 | 1M | DeepSeek Released 2026-04 Week change −1 Price $0.66 / $1.98 Length 1M | |||
| 1–112 | GPT-6 Astra | OpenAI | Rating 1465 ±40 | +10 | 1476rank 17–44 | $10 | $50 | 1.05M | OpenAI Released 2026-09 Week change +10 Price $10 / $50 Length 1.05M | |||
| 4–95 | GPT-5.6 Terra | OpenAI | Rating 1464 ±23 | +4 | 1467rank 28–53 | $2 | $12 | 1.05M | OpenAI Released 2026-07 Week change +4 Price $2 / $12 Length 1.05M | |||
| 10–91 | GPT-5.1 | OpenAI | Rating 1463 ±16 | 0 | 1456rank 49–72 | $1.25 | $10 | 400K | OpenAI Released 2025-11 Price $1.25 / $10 Length 400K | |||
| 7–94 | ERNIE 5.1 | Baidu | Rating 1463 ±21 | −1 | 1467rank 26–53 | — | — | 119K | — | Baidu Released — Week change −1 Price — Length 119K | ||
| 1–111 | Tencent HY3 | Tencent | Rating 1463 ±35 | −4 | 1454rank 48–76 | — | — | 256K | Tencent Released 2026-07 Week change −4 Price — Length 256K | |||
| 10–93 | ERNIE 5.0 (0110) | Baidu | Rating 1463 ±20 | 0 | 1446rank 63–88 | — | — | — | — | Baidu Released — Price — Length — | ||
| 10–93 | GPT-5.4 mini | OpenAI | Rating 1462 ±18 | 0 | 1447rank 62–87 | $0.75 | $4.5 | 400K | OpenAI Released 2026-03 Price $0.75 / $4.5 Length 400K | |||
| 1–102 | Grok 4.6 | xAI | Rating 1462 ±27 | +1 | 1456rank 48–72 | $2 | $6 | 500K | xAI Released 2026-08 Week change +1 Price $2 / $6 Length 500K | |||
| 10–93 | DeepSeek-V4 Pro (preview) | DeepSeek | Rating 1461 ±18 | +1 | 1455rank 49–72 | — | — | — | — | DeepSeek Released — Week change +1 Price — Length — | ||
| 15–91 | ChatGPT-4o (2025-03-26) | OpenAI | Rating 1461 ±11 | 0 | 1443rank 68–93 | — | — | 128K | OpenAI Released 2025-03 Price — Length 128K | |||
| 10–96 | GLM-5.2 | Z.ai | Rating 1460 ±21 | +5 | 1475rank 19–43 | $1.4 | $4.4 | 1M | Z.ai Released 2026-06 Week change +5 Price $1.4 / $4.4 Length 1M | |||
| 5–103 | Gemini 3.5 Flash-Lite | Rating 1459 ±25 | 0 | 1455rank 49–73 | $0.3 | $2.5 | 1.05M | Google Released 2026-07 Price $0.3 / $2.5 Length 1.05M | ||||
| 11–93 | GPT-5 Chat | OpenAI | Rating 1458 ±15 | 0 | 1426rank 91–124 | — | — | 128K | OpenAI Released 2025-08 Price — Length 128K | |||
| 1–116 | GPT-6 Sol | OpenAI | Rating 1458 ±40 | +7 | 1459rank 41–71 | $2 | $10 | 1.05M | OpenAI Released 2026-09 Week change +7 Price $2 / $10 Length 1.05M | |||
| 16–91 | o3 | OpenAI | Rating 1458 ±11 | 0 | 1432rank 84–114 | $2 | $8 | 200K | OpenAI Released 2025-04 Price $2 / $8 Length 200K | |||
| 15–93 | Claude Sonnet 4.5 | Anthropic | Rating 1457 ±13 | 0 | 1456rank 49–69 | $3 | $15 | 200K | Anthropic Released 2025-09 Price $3 / $15 Length 200K | |||
| 19–91 | Gemini 2.5 Pro | Rating 1456 ±9 | 0 | 1445rank 64–87 | $1.25 | $10 | 1M | Google Released 2025-06 Price $1.25 / $10 Length 1M | ||||
| 10–103 | GLM-5.3 Flash | Z.ai | Rating 1455 ±23 | +4 | 1476rank 19–43 | $0.15 | $0.5 | 1M | Z.ai Released 2026-08 Week change +4 Price $0.15 / $0.5 Length 1M | |||
| 15–98 | Gemini 3.1 Flash-Lite (preview) | Rating 1454 ±16 | +1 | 1433rank 83–112 | $0.25 | $1.5 | 1.05M | Google Released 2026-03 Week change +1 Price $0.25 / $1.5 Length 1.05M | ||||
| 16–98 | GPT-5.2 | OpenAI | Rating 1453 ±15 | 0 | 1437rank 76–103 | $1.75 | $14 | 400K | OpenAI Released 2025-12 Price $1.75 / $14 Length 400K | |||
| 1–124 | ERNIE 5.0 (preview, 1022) | Baidu | Rating 1451 ±40 | 0 | 1418rank 100–137 | — | — | — | — | Baidu Released — Price — Length — | ||
| 21–96 | Claude Opus 4.1 | Anthropic | Rating 1450 ±10 | 0 | 1450rank 54–80 | — | — | 200K | Anthropic Released 2025-08 Price — Length 200K | |||
| 16–107 | GPT-6 Luna | OpenAI | Rating 1449 ±20 | 0 | 1442rank 66–97 | $0.1 | $0.5 | 1.05M | OpenAI Released 2026-09 Price $0.1 / $0.5 Length 1.05M | |||
| 11–112 | MiMo-V2 Pro | Xiaomi | Rating 1449 ±24 | 0 | 1448rank 57–87 | — | — | 1.05M | Xiaomi Released 2026-03 Price — Length 1.05M | |||
| 19–103 | GPT-5 | OpenAI | Rating 1449 ±15 | 0 | 1435rank 77–111 | $1.25 | $10 | 400K | OpenAI Released 2025-08 Price $1.25 / $10 Length 400K | |||
| 14–112 | Grok 4.5 | xAI | Rating 1448 ±24 | −1 | 1466rank 33–55 | $2 | $6 | 500K | xAI Released 2026-07 Week change −1 Price $2 / $6 Length 500K | |||
| 20–103 | Kimi K2.5 | Moonshot | Rating 1447 ±15 | 0 | 1450rank 55–79 | — | — | 262.1K | Moonshot Released 2026-01 Price — Length 262.1K | |||
| 19–106 | GLM-5.1 | Z.ai | Rating 1447 ±17 | +5 | 1465rank 36–53 | $1.4 | $4.4 | 200K | Z.ai Released 2026-04 Week change +5 Price $1.4 / $4.4 Length 200K | |||
| 15–113 | Inkling | Thinking Machines | Rating 1447 ±23 | −2 | 1442rank 68–97 | $1.87 | $4.68 | 262.1K | Thinking Machines Released 2026-07 Week change −2 Price $1.87 / $4.68 Length 262.1K | |||
| 3–129 | MiMo-V2.6 Flash | Xiaomi | Rating 1447 ±40 | New | 1448rank 52–88 | $0.14 | $0.28 | 1.05M | Xiaomi Released 2026-09 Price $0.14 / $0.28 Length 1.05M | |||
| 11–119 | Qwen3.8 27B | Alibaba | Rating 1446 ±29 | +4 | 1437rank 75–108 | — | — | 262.1K | Alibaba Released 2026-08 Week change +4 Price — Length 262.1K | |||
| 21–103 | Qwen3.5 397B A17B | Alibaba | Rating 1446 ±15 | −1 | 1442rank 69–96 | $0.6 | $3.6 | 262.1K | Alibaba Released 2026-02 Week change −1 Price $0.6 / $3.6 Length 262.1K | |||
| 11–122 | Grok 4 Fast | xAI | Rating 1445 ±31 | 0 | 1419rank 102–136 | — | — | 2M | xAI Released 2025-09 Price — Length 2M | |||
| 20–111 | Grok 4.3 | xAI | Rating 1445 ±18 | 0 | 1442rank 68–97 | $1.25 | $2.5 | 1M | xAI Released 2026-04 Price $1.25 / $2.5 Length 1M | |||
| 19–113 | Claude Sonnet 5 | Anthropic | Rating 1443 ±22 | −1 | 1461rank 41–64 | $2 | $10 | 1M | Anthropic Released 2026-06 Week change −1 Price $2 / $10 Length 1M | |||
| 20–113 | Kimi K2.6 | Moonshot | Rating 1443 ±21 | 0 | 1461rank 41–65 | $0.95 | $4 | 262.1K | Moonshot Released 2026-04 Price $0.95 / $4 Length 262.1K | |||
| 19–116 | GLM-5 | Z.ai | Rating 1442 ±23 | 0 | 1457rank 47–70 | $1 | $3.2 | 204.8K | Z.ai Released 2026-02 Price $1 / $3.2 Length 204.8K | |||
| 21–116 | Qwen3.7 Plus | Alibaba | Rating 1440 ±20 | −1 | 1456rank 48–72 | $0.4 | $1.6 | 1M | Alibaba Released 2026-06 Week change −1 Price $0.4 / $1.6 Length 1M | |||
| 19–124 | Qwen3.5 Max (preview) | Alibaba | Rating 1438 ±26 | 0 | 1465rank 36–60 | — | — | — | — | Alibaba Released — Price — Length — | ||
| 25–117 | DeepSeek-V4 Flash | DeepSeek | Rating 1436 ±19 | 0 | 1436rank 77–109 | $0.15 | $0.6 | 1M | DeepSeek Released 2026-04 Price $0.15 / $0.6 Length 1M | |||
| 11–136 | Gemma 4 31B | Rating 1436 ±38 | −2 | 1452rank 48–85 | — | — | 262.1K | Google Released 2026-04 Week change −2 Price — Length 262.1K | ||||
| 21–126 | GLM-4.7 | Z.ai | Rating 1435 ±26 | 0 | 1441rank 65–102 | $0.6 | $2.2 | 204.8K | Z.ai Released 2025-12 Price $0.6 / $2.2 Length 204.8K | |||
| 21–125 | GPT-5.6 Luna | OpenAI | Rating 1435 ±24 | −1 | 1453rank 51–75 | $0.2 | $1.2 | 1.05M | OpenAI Released 2026-07 Week change −1 Price $0.2 / $1.2 Length 1.05M | |||
| 27–119 | DeepSeek-V4 Flash (preview) | DeepSeek | Rating 1435 ±18 | +1 | 1439rank 72–102 | — | — | — | — | DeepSeek Released — Week change +1 Price — Length — | ||
| 28–119 | MiniMax-M3 | MiniMax | Rating 1434 ±18 | +3 | 1440rank 69–101 | $0.3 | $1.2 | 1.05M | MiniMax Released 2026-06 Week change +3 Price $0.3 / $1.2 Length 1.05M | |||
| 30–123 | Qwen3.6 Plus | Alibaba | Rating 1432 ±19 | −1 | 1443rank 65–95 | $0.5 | $3 | 1M | Alibaba Released 2026-03 Week change −1 Price $0.5 / $3 Length 1M | |||
| 21–135 | DeepSeek-V3.2 (exp) | DeepSeek | Rating 1430 ±30 | 0 | 1425rank 90–126 | — | — | 163.8K | DeepSeek Released 2025-09 Price — Length 163.8K | |||
| 50–119 | GPT-4.1 | OpenAI | Rating 1428 ±12 | 0 | 1415rank 112–136 | $2 | $8 | 1.05M | OpenAI Released 2025-04 Price $2 / $8 Length 1.05M | |||
| 48–122 | Kimi K2 (instruct) | Moonshot | Rating 1427 ±13 | 0 | 1418rank 104–135 | — | — | 131.1K | Moonshot Released 2025-07 Price — Length 131.1K | |||
| 46–125 | Qwen3 Max (preview) | Alibaba | Rating 1427 ±16 | 0 | 1434rank 79–112 | — | — | 256K | — | Alibaba Released — Price — Length 256K | ||
| 47–125 | Grok 4.1 Fast Reasoning | xAI | Rating 1426 ±16 | 0 | 1430rank 88–114 | — | — | 2M | xAI Released 2025-11 Price — Length 2M | |||
| 10–162 | GPT-4o (2024-05) | OpenAI | Rating 1425 ±57 | 0 | 1346rank 190–214 | $5 | $15 | 128K | OpenAI Released 2024-05 Price $5 / $15 Length 128K | |||
| 40–133 | Kimi K2 (instruct, 2025-09) | Moonshot | Rating 1423 ±23 | +1 | 1419rank 102–135 | — | — | 262.1K | Moonshot Released 2025-09 Week change +1 Price — Length 262.1K | |||
| 19–150 | GLM-5V Turbo | Z.ai | Rating 1423 ±41 | −1 | 1434rank 76–114 | $1.2 | $4 | 200K | Z.ai Released 2026-04 Week change −1 Price $1.2 / $4 Length 200K | |||
| 21–150 | Mistral Medium 3.5 | Mistral | Rating 1422 ±38 | 0 | 1426rank 88–125 | $1.5 | $7.5 | 262.1K | Mistral Released 2026-04 Price $1.5 / $7.5 Length 262.1K | |||
| 38–137 | MiMo-V2 Omni | Xiaomi | Rating 1420 ±27 | −2 | 1431rank 83–119 | — | — | — | — | Xiaomi Released — Week change −2 Price — Length — | ||
| 54–129 | Kimi K2 Thinking Turbo | Moonshot | Rating 1420 ±14 | 0 | 1430rank 88–116 | — | — | — | Moonshot Released 2025-11 Price — Length — | |||
| 60–126 | Claude Opus 4 | Anthropic | Rating 1420 ±11 | 0 | 1426rank 91–124 | — | — | 200K | Anthropic Released 2025-05 Price — Length 200K | |||
| 50–133 | MiMo-V2.5 | Xiaomi | Rating 1420 ±19 | 0 | 1434rank 80–112 | $0.14 | $0.28 | 1.05M | Xiaomi Released 2026-04 Price $0.14 / $0.28 Length 1.05M | |||
| 52–131 | GLM-4.6 | Z.ai | Rating 1419 ±16 | −1 | 1424rank 96–125 | $0.6 | $2.2 | 204.8K | Z.ai Released 2025-09 Week change −1 Price $0.6 / $2.2 Length 204.8K | |||
| 60–129 | Grok 4 | xAI | Rating 1419 ±12 | 0 | 1411rank 117–140 | — | — | 256K | xAI Released 2025-07 Price — Length 256K | |||
| 52–133 | DeepSeek-V3.2 | DeepSeek | Rating 1418 ±17 | 0 | 1425rank 96–124 | — | — | 128K | DeepSeek Released 2025-12 Price — Length 128K | |||
| 23–156 | DeepSeek-V3.1 Terminus | DeepSeek | Rating 1417 ±39 | −3 | 1416rank 102–145 | — | — | 128K | DeepSeek Released 2025-09 Week change −3 Price — Length 128K | |||
| 61–136 | Grok 3 (preview, 02.24) | xAI | Rating 1414 ±16 | 0 | 1411rank 116–140 | — | — | — | — | xAI Released — Price — Length — | ||
| 62–133 | Mistral Large 3 | Mistral | Rating 1414 ±14 | −2 | 1414rank 112–136 | $0.5 | $1.5 | 262.1K | Mistral Released 2025-12 Week change −2 Price $0.5 / $1.5 Length 262.1K | |||
| 64–137 | DeepSeek-R1 (2025-05) | DeepSeek | Rating 1412 ±14 | 0 | 1421rank 100–132 | — | — | 131.1K | DeepSeek Released 2025-05 Price — Length 131.1K | |||
| 52–150 | Inkling Small | Thinking Machines | Rating 1410 ±26 | −6 | 1405rank 127–150 | $0.58 | $1.44 | 524.3K | Thinking Machines Released 2026-07 Week change −6 Price $0.58 / $1.44 Length 524.3K | |||
| 74–137 | o4-mini | OpenAI | Rating 1405 ±12 | 0 | 1391rank 144–169 | $1.1 | $4.4 | 200K | OpenAI Released 2025-04 Price $1.1 / $4.4 Length 200K | |||
| 60–156 | Qwen3 VL 235B A22B (instruct) | Alibaba | Rating 1404 ±27 | 0 | 1413rank 109–141 | — | — | 262.1K | — | Alibaba Released — Price — Length 262.1K | ||
| 81–137 | Qwen3 235B A22B (instruct) | Alibaba | Rating 1403 ±10 | 0 | 1422rank 103–126 | — | — | 128K | Alibaba Released 2025-07 Price — Length 128K | |||
| 62–155 | LongCat-Flash-Chat (exp, 2026-02) | Meituan | Rating 1403 ±25 | −2 | 1436rank 76–108 | — | — | — | — | Meituan Released — Week change −2 Price — Length — | ||
| 30–172 | Claude 3 Opus | Anthropic | Rating 1402 ±49 | 0 | 1322rank 222–248 | — | — | — | Anthropic Released 2024-02 Price — Length — | |||
| 70–150 | GPT-5.4 nano | OpenAI | Rating 1402 ±18 | +1 | 1401rank 134–153 | $0.2 | $1.25 | 400K | OpenAI Released 2026-03 Week change +1 Price $0.2 / $1.25 Length 400K | |||
| 78–148 | MiniMax-M2.7 | MiniMax | Rating 1401 ±15 | −2 | 1415rank 112–136 | $0.3 | $1.2 | 204.8K | MiniMax Released 2026-03 Week change −2 Price $0.3 / $1.2 Length 204.8K | |||
| 70–150 | DeepSeek-V3.1 | DeepSeek | Rating 1401 ±19 | −1 | 1417rank 104–136 | — | — | 128K | DeepSeek Released 2025-08 Week change −1 Price — Length 128K | |||
| 83–143 | Mistral Medium 3.1 | Mistral | Rating 1401 ±11 | 0 | 1408rank 126–145 | $0.4 | $2 | 262.1K | Mistral Released 2025-08 Price $0.4 / $2 Length 262.1K | |||
| 78–150 | GPT-5 mini | OpenAI | Rating 1400 ±16 | 0 | 1390rank 144–169 | $0.25 | $2 | 400K | OpenAI Released 2025-08 Price $0.25 / $2 Length 400K | |||
| 88–140 | Gemini 2.5 Flash | Rating 1400 ±9 | 0 | 1409rank 121–140 | $0.3 | $2.5 | 1M | Google Released 2025-06 Price $0.3 / $2.5 Length 1M | ||||
| 78–150 | Gemini 2.5 Flash (preview, 2025-09) | Rating 1399 ±17 | 0 | 1403rank 127–152 | — | — | 1M | Google Released 2025-09 Price — Length 1M | ||||
| 62–159 | Qwen3 Max (instruct) | Alibaba | Rating 1399 ±29 | 0 | 1424rank 93–129 | — | — | 258K | Alibaba Released 2025-09 Price — Length 258K | |||
| 88–150 | DeepSeek-V3 (2025-03) | DeepSeek | Rating 1396 ±12 | 0 | 1395rank 139–164 | — | — | 163.8K | DeepSeek Released 2025-03 Price — Length 163.8K | |||
| 52–173 | Kimi K2.5 Instant | Moonshot | Rating 1394 ±42 | 0 | 1431rank 83–120 | — | — | — | Moonshot Released 2026-01 Price — Length — | |||
| 91–154 | Mistral Medium 3 | Mistral | Rating 1391 ±12 | 0 | 1387rank 149–171 | $0.4 | $2 | 128K | Mistral Released 2025-05 Price $0.4 / $2 Length 128K | |||
| 92–153 | Qwen3 235B A22B | Alibaba | Rating 1391 ±11 | 0 | 1402rank 131–153 | $0.7 | $2.8 | 128K | Alibaba Released 2025-04 Price $0.7 / $2.8 Length 128K | |||
| 91–154 | Claude Sonnet 4 | Anthropic | Rating 1391 ±11 | 0 | 1402rank 131–153 | — | — | 200K | Anthropic Released 2025-05 Price — Length 200K | |||
| 21–192 | Claude 3.5 Sonnet (2024-06) | Anthropic | Rating 1389 ±70 | 0 | 1343rank 195–220 | — | — | 200K | Anthropic Released 2024-06 Price — Length 200K | |||
| 86–164 | Qwen3.5 122B A10B | Alibaba | Rating 1386 ±24 | +1 | 1417rank 107–135 | $0.4 | $3.2 | 262.1K | Alibaba Released 2026-02 Week change +1 Price $0.4 / $3.2 Length 262.1K | |||
| 80–168 | MiMo-V2 Flash | Xiaomi | Rating 1386 ±28 | 0 | 1392rank 144–167 | — | — | 262.1K | Xiaomi Released 2025-12 Price — Length 262.1K | |||
| 97–159 | Claude 3.5 Sonnet (2024-10) | Anthropic | Rating 1385 ±14 | 0 | 1374rank 167–177 | — | — | 200K | Anthropic Released 2024-10 Price — Length 200K | |||
| 96–159 | GLM-4.5 | Z.ai | Rating 1385 ±15 | 0 | 1411rank 115–145 | $0.6 | $2.2 | 131.1K | Z.ai Released 2025-08 Price $0.6 / $2.2 Length 131.1K | |||
| 88–165 | Hunyuan-TurboS (2025-04) | Tencent | Rating 1385 ±24 | 0 | 1383rank 151–175 | — | — | 131.1K | Tencent Released 2025-04 Price — Length 131.1K | |||
| 96–167 | Qwen3 235B A22B (thinking) | Alibaba | Rating 1380 ±21 | 0 | 1400rank 131–160 | — | — | 262.1K | Alibaba Released 2025-07 Price — Length 262.1K | |||
| 103–162 | GPT-4.1 mini | OpenAI | Rating 1379 ±12 | 0 | 1383rank 154–172 | — | — | 1.05M | OpenAI Released 2025-04 Price — Length 1.05M | |||
| 104–164 | Claude 3.7 Sonnet | Anthropic | Rating 1376 ±14 | 0 | 1388rank 148–169 | — | — | 200K | Anthropic Released 2025-02 Price — Length 200K | |||
| 99–174 | Qwen3.5 35B A3B | Alibaba | Rating 1374 ±23 | 0 | 1394rank 140–165 | $0.25 | $2 | 262.1K | Alibaba Released 2026-02 Price $0.25 / $2 Length 262.1K | |||
| 104–173 | MiniMax-M2.5 | MiniMax | Rating 1371 ±20 | 0 | 1391rank 144–169 | $0.3 | $1.2 | 204.8K | MiniMax Released 2026-02 Price $0.3 / $1.2 Length 204.8K | |||
| 114–165 | Claude Haiku 4.5 | Anthropic | Rating 1371 ±11 | +1 | 1414rank 114–135 | $1 | $5 | 200K | Anthropic Released 2025-10 Week change +1 Price $1 / $5 Length 200K | |||
| 105–172 | Gemini 2.0 Flash | Rating 1370 ±16 | 0 | 1360rank 176–198 | — | — | — | Google Released 2025-02 Price — Length — | ||||
| 105–173 | Qwen3 Next 80B A3B (instruct) | Alibaba | Rating 1370 ±19 | +1 | 1399rank 136–159 | $0.5 | $2 | 129K | Alibaba Released 2025-09 Week change +1 Price $0.5 / $2 Length 129K | |||
| 106–172 | Qwen3 Coder 480B A35B (instruct) | Alibaba | Rating 1370 ±15 | 0 | 1388rank 148–171 | $1.5 | $7.5 | 262.1K | Alibaba Released 2025-07 Price $1.5 / $7.5 Length 262.1K | |||
| 106–172 | Step 3.5 Flash | StepFun | Rating 1369 ±16 | 0 | 1393rank 144–166 | $0.1046 | $0.3138 | 256K | StepFun Released 2026-02 Price $0.1046 / $0.3138 Length 256K | |||
| 114–168 | Gemma 3 27B | Rating 1369 ±12 | 0 | 1365rank 174–188 | — | — | 128K | Google Released 2025-03 Price — Length 128K | ||||
| 67–197 | GPT-4 Turbo (preview, 2023-11) | OpenAI | Rating 1368 ±57 | 0 | 1313rank 231–261 | — | — | — | OpenAI Released 2023-11 Price — Length — | |||
| 117–171 | Gemini 2.5 Flash-Lite (preview, 2025-06) | Rating 1367 ±12 | 0 | 1375rank 165–178 | — | — | 1.05M | Google Released 2025-06 Price — Length 1.05M | ||||
| 105–179 | LongCat-Flash-Chat | Meituan | Rating 1367 ±23 | 0 | 1401rank 127–159 | — | — | 131.1K | — | Meituan Released — Price — Length 131.1K | ||
| 103–183 | Qwen3.5 27B | Alibaba | Rating 1366 ±26 | 0 | 1409rank 117–146 | $0.3 | $2.4 | 262.1K | Alibaba Released 2026-02 Price $0.3 / $2.4 Length 262.1K | |||
| 103–186 | Qwen3 VL 235B A22B | Alibaba | Rating 1364 ±28 | 0 | 1395rank 137–167 | — | — | 131.1K | — | Alibaba Released — Price — Length 131.1K | ||
| 105–184 | MiniMax-M2.1 (preview) | MiniMax | Rating 1364 ±25 | 0 | 1385rank 150–171 | — | — | — | — | MiniMax Released — Price — Length — | ||
| 115–175 | Qwen3.5 Flash | Alibaba | Rating 1364 ±17 | −1 | 1396rank 139–163 | $0.1 | $0.4 | 1M | Alibaba Released 2026-02 Week change −1 Price $0.1 / $0.4 Length 1M | |||
| 70–200 | GPT-4 Turbo | OpenAI | Rating 1363 ±57 | 0 | 1325rank 222–246 | — | — | — | OpenAI Released 2024-04 Price — Length — | |||
| 74–197 | GPT-4 Turbo (preview, 2024-01) | OpenAI | Rating 1363 ±54 | 0 | 1313rank 231–261 | — | — | — | OpenAI Released 2024-01 Price — Length — | |||
| 120–175 | Gemini 2.5 Flash-Lite (preview, 2025-09) | Rating 1363 ±15 | 0 | 1379rank 160–175 | — | — | 1M | Google Released 2025-09 Price — Length 1M | ||||
| 104–188 | Hunyuan-T1 | Tencent | Rating 1360 ±30 | 0 | 1387rank 144–172 | — | — | 131.1K | Tencent Released 2025-07 Price — Length 131.1K | |||
| 118–184 | Qwen2.5 Max | Alibaba | Rating 1358 ±20 | 0 | 1374rank 167–178 | — | — | — | Alibaba Released 2025-01 Price — Length — | |||
| 114–187 | Qwen3 Next 80B A3B | Alibaba | Rating 1358 ±22 | −2 | 1369rank 170–186 | $0.5 | $6 | 131.1K | Alibaba Released 2025-09 Week change −2 Price $0.5 / $6 Length 131.1K | |||
| 73–203 | Gemini 1.5 Pro 001 | Rating 1358 ±60 | 0 | 1324rank 222–246 | — | — | — | Google Released 2024-05 Price — Length — | ||||
| 125–183 | MiniMax-M1 | MiniMax | Rating 1352 ±11 | 0 | 1364rank 175–191 | — | — | 1M | MiniMax Released 2025-06 Price — Length 1M | |||
| 62–208 | Gemma 2 27B | Rating 1351 ±77 | 0 | 1290rank 263–279 | — | — | 8.2K | Google Released 2024-06 Price — Length 8.2K | ||||
| 127–184 | Command A | Cohere | Rating 1350 ±11 | 0 | 1354rank 184–210 | $2.5 | $10 | 256K | Cohere Released 2025-03 Price $2.5 / $10 Length 256K | |||
| 105–197 | NVIDIA Nemotron 3 Ultra 550B A55B (NVFP4) | NVIDIA | Rating 1349 ±38 | +1 | 1426rank 88–126 | — | — | — | — | NVIDIA Released — Week change +1 Price — Length — | ||
| 129–188 | Qwen3 30B A3B (instruct) | Alibaba | Rating 1344 ±15 | 0 | 1382rank 154–174 | — | — | 131.1K | Alibaba Released 2025-07 Price — Length 131.1K | |||
| 129–190 | Grok 3 Mini | xAI | Rating 1344 ±16 | 0 | 1364rank 174–193 | — | — | 131.1K | xAI Released 2025-06 Price — Length 131.1K | |||
| 123–194 | Trinity Large (preview) | Arcee AI | Rating 1343 ±26 | 0 | 1379rank 160–176 | — | — | 131.1K | — | Arcee AI Released — Price — Length 131.1K | ||
| 123–195 | Trinity Large | Arcee AI | Rating 1342 ±26 | 0 | 1367rank 171–188 | — | — | 262.1K | Arcee AI Released 2026-04 Price — Length 262.1K | |||
| 132–190 | GLM-4.5 Air | Z.ai | Rating 1342 ±14 | 0 | 1373rank 168–181 | $0.2 | $1.1 | 131.1K | Z.ai Released 2025-07 Price $0.2 / $1.1 Length 131.1K | |||
| 132–190 | Mistral Small 3.2 | Mistral | Rating 1342 ±15 | 0 | 1356rank 179–208 | $0.1 | $0.3 | 128K | Mistral Released 2025-06 Price $0.1 / $0.3 Length 128K | |||
| 137–190 | Claude 3.5 Haiku | Anthropic | Rating 1339 ±13 | 0 | 1325rank 222–243 | — | — | 200K | Anthropic Released 2024-10 Price — Length 200K | |||
| 125–197 | GPT-5 nano | OpenAI | Rating 1338 ±26 | 0 | 1338rank 195–230 | $0.05 | $0.4 | 400K | OpenAI Released 2025-08 Price $0.05 / $0.4 Length 400K | |||
| 92–208 | GPT-4 (2023-03) | OpenAI | Rating 1337 ±64 | 0 | 1288rank 263–280 | — | — | — | OpenAI Released 2023-03 Price — Length — | |||
| 141–191 | Grok 3 Mini (beta) | xAI | Rating 1336 ±14 | 0 | 1358rank 177–204 | — | — | — | xAI Released 2025-04 Price — Length — | |||
| 143–195 | GPT-OSS 120B | OpenAI | Rating 1331 ±15 | 0 | 1352rank 185–211 | — | — | 128K | OpenAI Released 2025-08 Price — Length 128K | |||
| 144–193 | Llama 4 Maverick | Meta | Rating 1330 ±13 | 0 | 1327rank 215–242 | — | — | 524.3K | Meta Released 2025-04 Price — Length 524.3K | |||
| 146–197 | o3-mini | OpenAI | Rating 1327 ±12 | 0 | 1364rank 174–193 | $1.1 | $4.4 | 200K | OpenAI Released 2025-01 Price $1.1 / $4.4 Length 200K | |||
| 120–207 | INTELLECT-3 | Prime Intellect | Rating 1327 ±45 | 0 | 1356rank 176–211 | — | — | — | — | Prime Intellect Released — Price — Length — | ||
| 143–202 | Amazon Nova Experimental Chat (11.10) | Amazon | Rating 1324 ±22 | 0 | 1364rank 175–191 | — | — | — | — | Amazon Released — Price — Length — | ||
| 151–197 | Llama 4 Scout | Meta | Rating 1322 ±13 | 0 | 1322rank 222–252 | — | — | 128K | Meta Released 2025-04 Price — Length 128K | |||
| 133–206 | GLM-4.5V | Z.ai | Rating 1321 ±34 | 0 | 1352rank 179–213 | $0.6 | $1.8 | 64K | Z.ai Released 2025-08 Price $0.6 / $1.8 Length 64K | |||
| 150–202 | Llama 3.3 70B (instruct) | Meta | Rating 1319 ±17 | 0 | 1318rank 227–252 | — | — | 131.1K | Meta Released 2024-12 Price — Length 131.1K | |||
| 120–210 | GPT-4 (2023-06) | OpenAI | Rating 1317 ±58 | 0 | 1276rank 273–288 | — | — | — | OpenAI Released 2023-06 Price — Length — | |||
| 144–206 | Llama 3.3 Nemotron Super 49B (v1.5) | NVIDIA | Rating 1315 ±29 | 0 | 1343rank 186–227 | — | — | 131.1K | — | NVIDIA Released — Price — Length 131.1K | ||
| 123–210 | Claude 3 Sonnet | Anthropic | Rating 1314 ±54 | 0 | 1281rank 268–288 | — | — | — | Anthropic Released 2024-02 Price — Length — | |||
| 153–204 | Magistral Medium | Mistral | Rating 1312 ±16 | 0 | 1305rank 243–267 | — | — | — | Mistral Released 2025-06 Price — Length — | |||
| 149–207 | Amazon Nova Experimental Chat (10.20) | Amazon | Rating 1309 ±28 | 0 | 1348rank 185–215 | — | — | — | — | Amazon Released — Price — Length — | ||
| 144–208 | NVIDIA Nemotron 3 Super 120B A12B | NVIDIA | Rating 1308 ±35 | 0 | 1360rank 175–204 | — | — | 262.1K | NVIDIA Released 2026-03 Price — Length 262.1K | |||
| 143–210 | MiniMax-M2 | MiniMax | Rating 1308 ±37 | 0 | 1344rank 188–225 | $0.3 | $1.2 | 1M | MiniMax Released 2025-10 Price $0.3 / $1.2 Length 1M | |||
| 158–205 | Gemma 3n E4B | Rating 1305 ±15 | 0 | 1318rank 225–256 | — | — | — | — | Google Released — Price — Length — | |||
| 160–205 | Qwen3 30B A3B | Alibaba | Rating 1304 ±14 | 0 | 1327rank 214–242 | — | — | 128K | Alibaba Released 2025-04 Price — Length 128K | |||
| 149–210 | NVIDIA Nemotron 3.5 Lightning 30B A3B (NVFP4) | NVIDIA | Rating 1303 ±35 | −4 | 1353rank 182–211 | — | — | — | — | NVIDIA Released — Week change −4 Price — Length — | ||
| 130–211 | Command R Plus | Cohere | Rating 1303 ±56 | 0 | 1262rank 287–298 | — | — | — | — | Cohere Released — Price — Length — | ||
| 140–211 | Claude 3 Haiku | Anthropic | Rating 1299 ±53 | 0 | 1262rank 287–298 | — | — | 200K | Anthropic Released 2024-03 Price — Length 200K | |||
| 153–210 | GLM-4.7 Flash | Z.ai | Rating 1295 ±33 | 0 | 1365rank 172–192 | — | — | 202.8K | Z.ai Released 2026-01 Price — Length 202.8K | |||
| 132–212 | Gemini 1.5 Flash | Rating 1294 ±62 | 0 | 1287rank 264–282 | — | — | — | Google Released 2024-05 Price — Length — | ||||
| 157–210 | Solar Pro 4 | Upstage | Rating 1291 ±34 | 0 | 1387rank 148–171 | $0.3 | $1.2 | 524.3K | Upstage Released 2026-08 Price $0.3 / $1.2 Length 524.3K | |||
| 159–210 | Step 3 | StepFun | Rating 1290 ±28 | 0 | 1349rank 184–215 | — | — | — | — | StepFun Released — Price — Length — | ||
| 169–210 | QwQ 32B | Alibaba | Rating 1289 ±17 | 0 | 1336rank 199–230 | — | — | 32.8K | Alibaba Released 2025-03 Price — Length 32.8K | |||
| 161–210 | Amazon Nova 2 Lite | Amazon | Rating 1287 ±30 | 0 | 1335rank 199–232 | $0.3 | $2.5 | 1M | Amazon Released 2025-12 Price $0.3 / $2.5 Length 1M | |||
| 170–210 | Step 1o Turbo (2025-06) | StepFun | Rating 1287 ±16 | 0 | 1320rank 222–255 | — | — | — | — | StepFun Released — Price — Length — | ||
| 163–211 | Ling Flash 2.0 | Ant Group | Rating 1281 ±34 | 0 | 1343rank 189–224 | — | — | 131K | — | Ant Group Released — Price — Length 131K | ||
| 169–210 | Hunyuan-Large-Vision | Tencent | Rating 1281 ±26 | 0 | 1294rank 252–280 | — | — | — | — | Tencent Released — Price — Length — | ||
| 144–212 | Command R | Cohere | Rating 1279 ±63 | 0 | 1250rank 294–305 | $0.15 | $0.6 | 128K | Cohere Released 2024-08 Price $0.15 / $0.6 Length 128K | |||
| 174–210 | Mistral Small 3.1 | Mistral | Rating 1279 ±13 | 0 | 1303rank 250–267 | — | — | 131.1K | Mistral Released 2025-03 Price — Length 131.1K | |||
| 143–212 | GPT-4o mini | OpenAI | Rating 1277 ±67 | 0 | 1318rank 228–254 | — | — | 128K | OpenAI Released 2024-07 Price — Length 128K | |||
| 173–211 | GPT-OSS 20B | OpenAI | Rating 1275 ±22 | 0 | 1317rank 223–260 | — | — | 131K | OpenAI Released 2025-08 Price — Length 131K | |||
| 170–212 | Ring Flash 2.0 | Ant Group | Rating 1271 ±31 | −1 | 1322rank 219–252 | — | — | — | — | Ant Group Released — Week change −1 Price — Length — | ||
| 163–212 | Llama 3 70B (instruct) | Meta | Rating 1265 ±50 | 0 | 1277rank 273–288 | — | — | 8.2K | Meta Released 2024-04 Price — Length 8.2K | |||
| 178–212 | NVIDIA Nemotron 3 Nano 30B A3B (BF16) | NVIDIA | Rating 1257 ±27 | −1 | 1314rank 230–261 | — | — | 65.5K | — | NVIDIA Released — Week change −1 Price — Length 65.5K | ||
| 172–212 | OLMo 3 32B Think | Ai2 | Rating 1255 ±47 | 0 | 1306rank 238–267 | — | — | — | — | Ai2 Released — Price — Length — | ||
| 169–213 | Mixtral 8x22B (instruct, v0.1) | Mistral | Rating 1244 ±64 | 0 | 1230rank 302–316 | — | — | 65.5K | Mistral Released 2024-04 Price — Length 65.5K | |||
| 183–212 | OLMo 3.1 32B (instruct) | Ai2 | Rating 1238 ±34 | 0 | 1329rank 206–241 | — | — | — | — | Ai2 Released — Price — Length — | ||
| 180–213 | Granite 4.0 H Small | IBM | Rating 1229 ±46 | 0 | 1288rank 261–287 | — | — | 131.1K | — | IBM Released — Price — Length 131.1K | ||
| 176–213 | GPT-3.5 Turbo (2024-01) | OpenAI | Rating 1227 ±60 | 0 | 1226rank 303–317 | — | — | 16.4K | OpenAI Released 2024-01 Price — Length 16.4K | |||
| 183–213 | Mistral Large (2024-02) | Mistral | Rating 1213 ±59 | 0 | 1243rank 298–308 | — | — | 32K | Mistral Released 2024-02 Price — Length 32K | |||
| 199–213 | OLMo 3.1 32B Think | Ai2 | Rating 1206 ±35 | 0 | 1286rank 263–287 | — | — | — | — | Ai2 Released — Price — Length — | ||
| 195–213 | Llama 3 8B (instruct) | Meta | Rating 1200 ±54 | 0 | 1224rank 307–317 | — | — | — | Meta Released 2024-04 Price — Length — | |||
| 207–213 | Mixtral 8x7B (instruct, v0.1) | Mistral | Rating 1135 ±64 | 0 | 1197rank 320–330 | — | — | 32K | Mistral Released 2023-12 Price — Length 32K |
How to read this page
- These ratings exclude the effect of response length and formatting. Differences where the ± ranges overlap are within the margin of error, so about the same.
- In the Supports column the icons are, from left: can use tools / can read images / can answer in a fixed format (JSON); faded means not supported or unknown.
- Open-weights models have their contents (the weights) published, so you can also run them on your own computer or server. Models without the open-weights mark are normally used through the developer's own services (apps or API); for some models the weights status is unknown.
- Names such as ChatGPT next to a model are the consumer services its developer offers. Check on the service itself whether that model is available there.
Data: Arena, Epoch AI, Swallow LLM team (CC BY 4.0), Models.dev (MIT), updated 2026-10-24, data sources