AI model leaderboard
222 ranked models by overall score and by category. Scores carry 90% intervals: when two intervals overlap, the order between those models is not certain.
Columns:
222 of 891 models
| Features | Intelligence | Price | Speed | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Select to compare | Type | Mode | ||||||||||||||||
| 1 | Claude Opus 5.5Verified | Anthropic | Proprietary | Reasoning | 1M | — | Sep 22, 2026 | 86.7 82–92 | 87.5 | 97.3 | 86.1 | 65.3 | 1516 | $4.00 | $20.00 | $8.00✓ | — | |
| 2 | GPT-6.1 SolVerified | OpenAI | Proprietary | Reasoning | 1.05M | — | Sep 29, 2026 | 84.2 80–88 | 74.1 | 97.3 | 90.5 | — | 1448 | $2.00 | $10.00 | $4.00✓ | — | |
| 3 | GPT-6 AstraVerified | OpenAI | Proprietary | Reasoning | 1.05M | — | Sep 3, 2026 | 84.0 80–89 | 76.4 | 97.3 | 93.3 | 86.5 | 1443 | $10.00 | $50.00 | $20.00✓ | — | |
| 4 | Claude Fable 5.1Verified | Anthropic | Proprietary | Reasoning | 1M | — | Sep 1, 2026 | 83.2 80–87 | 91.2 | 96.8 | 85.2 | 59.8 | 1512 | $10.00 | $50.00 | $20.00✓ | — | |
| 5 | Gemini 4 ArgonVerified | Proprietary | Reasoning | 1M | — | Sep 30, 2026 | 82.9 80–86 | 74.0 | 92.8 | 86.9 | 79.6 | 1532 | $2.00 | $10.00 | $4.00✓ | — | ||
| 6 | Claude Sonnet 5.5Verified | Anthropic | Proprietary | Reasoning | 1M | — | Sep 28, 2026 | 82.2 76–88 | 87.5 | 95.2 | 81.8 | 78.8 | 1470 | $2.00 | $10.00 | $4.00✓ | — | |
| 7 | Claude Fable 5Verified | Anthropic | Proprietary | Reasoning | 1M | — | Jun 9, 2026 | 81.3 78–84 | 90.3 | 96.0 | 84.3 | 82.9 | 1491 | $10.00 | $50.00 | $20.00✓ | — | |
| 8 | Claude Opus 5Verified | Anthropic | Proprietary | Reasoning | 1M | — | Jul 24, 2026 | 80.1 77–83 | 90.4 | 91.6 | 81.0 | 85.2 | 1508 | $5.00 | $25.00 | $10.00✓ | — | |
| 9 | GPT-6 SolVerified | OpenAI | Proprietary | Reasoning | 1.05M | — | Sep 22, 2026 | 78.6 75–82 | 77.5 | 97.3 | 73.1 | 73.7 | 1398 | $2.00 | $10.00 | $4.00✓ | — | |
| 10 | GPT-5.6 SolVerified | OpenAI | Proprietary | Reasoning | 1.05M | — | Jul 9, 2026 | 75.3 73–78 | 64.7 | 95.8 | 76.4 | 83.7 | 1457 | $4.00 | $20.00 | $8.00✓ | — | |
| 11 | Muse Wonder FullProvisional | Meta | Proprietary | Reasoning | 1M | — | Oct 12, 2026 | 74.8 60–89 | 69.0 | — | 82.5 | — | — | — | — | — | — | |
| 12 | MiMo-V2.6-ProProvisional | Xiaomi | Open weights | Reasoning | 1M | 1.02T | Sep 22, 2026 | 73.7 64–83 | 63.3 | — | 82.5 | 77.8 | 1491 | $0.43 | $0.87 | $0.54 | — | |
| 13 | GPT-5.5 ProProvisional | OpenAI | Proprietary | Reasoning | 1M | — | Apr 23, 2026 | 73.5 59–88 | — | 94.0 | 78.9 | 80.4 | — | $30.00 | $180.00 | $67.50✓ | — | |
| 14 | Muse WonderProvisional | Meta | Proprietary | Reasoning | 1M | — | Oct 12, 2026 | 71.5 57–86 | — | — | 80.4 | — | 1501 | $4.00 | $20.00 | $8.00 | — | |
| 15 | GPT-5.6 TerraVerified | OpenAI | Proprietary | Reasoning | 1.05M | — | Jul 9, 2026 | 70.2 67–74 | 64.3 | 90.1 | 69.1 | 76.0 | 1447 | $2.00 | $12.00 | $4.50✓ | — | |
| 16 | Claude Opus 4.8Verified | Anthropic | Proprietary | Reasoning | 1M | — | May 28, 2026 | 70.0 66–74 | 75.1 | 84.4 | 62.8 | 74.1 | 1461 | $5.00 | $25.00 | $10.00✓ | — | |
| 17 | Kimi K3Verified | Moonshot AI | Other | Reasoning | 1.05M | — | Jul 16, 2026 | 70.0 66–74 | 74.6 | — | 69.8 | 81.9 | 1475 | $3.00 | $15.00 | $6.00 | — | |
| 18 | Qwen3.8 MaxVerified | Alibaba | Open weights | Reasoning | 1M | — | Aug 3, 2026 | 69.7 66–74 | 70.6 | 78.9 | 87.0 | 82.9 | 1483 | — | — | — | — | |
| 19 | Step 5 PreviewProvisional | StepFun | Open weights | Reasoning | 1M | 604B | Sep 20, 2026 | 69.6 60–79 | 77.6 | — | 82.5 | 78.5 | 1441 | $1.00 | $2.70 | $1.43 | — | |
| 20 | GPT-5.5Verified | OpenAI | Proprietary | Reasoning | 1M | — | Apr 23, 2026 | 69.2 63–75 | 55.5 | 91.2 | 70.3 | 81.7 | 1471 | $5.00 | $30.00 | $11.25✓ | — | |
| 21 | Gemini 3.8 FlashVerified | Proprietary | Reasoning | 1M | — | Sep 2, 2026 | 69.2 64–75 | 77.5 | 69.7 | 74.3 | 72.6 | 1499 | $0.75 | $3.75 | $1.50✓ | — | ||
| 22 | GPT-5.4 ProProvisional | OpenAI | Proprietary | Reasoning | 1.05M | — | Mar 5, 2026 | 68.7 54–83 | — | 86.5 | 78.1 | 79.3 | — | $30.00 | $180.00 | $67.50 | — | |
| 23 | Claude Opus 4.7 (Adaptive)Provisional | Anthropic | Proprietary | Reasoning | 1M | — | Apr 16, 2026 | 68.7 54–83 | 65.6 | — | 57.4 | 71.8 | — | $5.00 | $25.00 | $10.00 | — | |
| 24 | Ling 3.1 FlashProvisional | InclusionAI | Open weights | Reasoning | 262K | 572B | Sep 29, 2026 | 68.1 54–82 | 69.1 | — | 82.0 | 82.3 | — | $0.075 | $0.23 | $0.11 | — | |
| 25 | GLM-5.3Verified | Z.AI | Open weights | Reasoning | 1M | 753B | Aug 14, 2026 | 68.0 63–72 | 58.6 | 71.5 | 79.8 | 74.5 | 1472 | $0.079 | $1.40 | $0.41 | — | |
| 26 | Claude Haiku 5.5Provisional | Anthropic | Proprietary | Reasoning | 1M | — | Oct 7, 2026 | 67.2 53–82 | 64.8 | 79.1 | 60.1 | — | — | $0.10 | $0.50 | $0.20✓ | — | |
| 27 | MiniMax M3.1 FlashProvisional | MiniMax | Proprietary | Reasoning | 1M | — | Oct 19, 2026 | 67.1 53–81 | — | — | 79.8 | 73.7 | — | $0.15 | $0.60 | $0.26 | — | |
| 28 | Grok 4.6Verified | xAI | Proprietary | Reasoning | 500K | — | Aug 12, 2026 | 67.1 64–70 | 77.3 | 70.1 | 61.4 | 77.6 | 1428 | $2.00 | $6.00 | $3.00✓ | — | |
| 29 | Gemini 3.7 FlashVerified | Proprietary | Reasoning | 1M | — | Aug 13, 2026 | 66.9 61–73 | 78.6 | 74.8 | 81.6 | 64.7 | 1487 | $0.75 | $3.75 | $1.50 | — | ||
| 30 | GPT-5.4Verified | OpenAI | Proprietary | Reasoning | 1.05M | — | Mar 5, 2026 | 66.7 62–71 | 47.1 | 82.0 | 64.2 | 80.3 | 1469 | $2.50 | $15.00 | $5.63✓ | — | |
| 31 | GPT-5.2 ProProvisional | OpenAI | Proprietary | Reasoning | 400K | — | Dec 11, 2025 | 66.7 57–76 | — | — | — | — | — | $21.00 | $168.00 | $57.75 | — | |
| 32 | GPT-6 LunaVerified | OpenAI | Proprietary | Reasoning | 1.05M | — | Sep 22, 2026 | 66.6 62–71 | 66.3 | 83.7 | 59.2 | 73.3 | 1392 | $0.10 | $0.50 | $0.20✓ | — | |
| 33 | Muse Spark 1.1Verified | Meta | Proprietary | Reasoning | 1M | — | Jul 9, 2026 | 66.1 58–75 | 60.2 | — | 78.4 | 66.9 | 1478 | $1.25 | $4.25 | $2.00 | — | |
| 34 | Muse Spark 1.2Verified | Meta | Proprietary | Reasoning | 1M | — | Aug 5, 2026 | 65.9 60–72 | 62.9 | — | 79.3 | 75.6 | 1484 | $1.25 | $4.25 | $2.00 | — | |
| 35 | DeepSeek V4.1 Flash 1017Verified | DeepSeek | Open weights | Reasoning | 1M | 763B | Oct 17, 2026 | 65.7 61–71 | 62.9 | 70.1 | 82.5 | — | 1463 | $0.15 | $0.60 | $0.26✓ | — | |
| 36 | Claude Opus 4.7Provisional | Anthropic | Proprietary | Non-reasoning | 1M | — | Apr 16, 2026 | 65.5 56–75 | 69.0 | 72.9 | 31.4 | 37.6 | 1490 | $5.00 | $25.00 | $10.00✓ | — | |
| 37 | Claude Sonnet 5Verified | Anthropic | Proprietary | Reasoning | 1M | — | Jun 30, 2026 | 64.9 60–70 | 62.8 | 69.4 | 81.3 | 77.5 | 1442 | $2.00 | $10.00 | $4.00✓ | — | |
| 38 | Gemini 3.1 ProProvisional | Proprietary | Reasoning | 1M | — | Feb 19, 2026 | 64.7 55–74 | 78.1 | 65.0 | 58.2 | 69.0 | — | $2.00 | $12.00 | $4.50✓ | — | ||
| 39 | MiMo-V2.6-FlashProvisional | Xiaomi | Open weights | Reasoning | 1M | 311B | Sep 22, 2026 | 64.6 55–74 | 64.1 | — | 76.0 | 75.7 | 1455 | $0.14 | $0.28 | $0.17 | — | |
| 40 | GPT-5.6 LunaVerified | OpenAI | Proprietary | Reasoning | 1.05M | — | Jul 9, 2026 | 64.4 59–69 | 56.4 | 84.0 | 58.2 | 70.2 | 1431 | $0.20 | $1.20 | $0.45✓ | — | |
| 41 | dots3-note PreviewProvisional | Dots Studio | Open weights | Reasoning | 512K | — | Aug 14, 2026 | 64.1 50–78 | 57.2 | — | 76.6 | 71.1 | — | — | — | — | — | |
| 42 | Grok 4.5Verified | xAI | Proprietary | Reasoning | 500K | — | Jul 8, 2026 | 63.3 58–69 | 67.7 | 62.9 | 54.1 | 74.3 | 1448 | $2.00 | $6.00 | $3.00✓ | — | |
| 43 | DeepSeek V4 Pro 0813Provisional | DeepSeek | Open weights | Reasoning | 1M | 1.65T | Aug 13, 2026 | 63.2 49–78 | 59.4 | 87.4 | 60.7 | 73.5 | — | $0.66 | $1.98 | $0.99✓ | — | |
| 44 | Qwen3.8-Flash-NextProvisional | Alibaba | Open weights | Reasoning | 262K | 180B | Aug 26, 2026 | 62.9 49–77 | 58.6 | — | 79.8 | 40.0 | — | — | — | — | — | |
| 45 | Gemini 3.6 FlashVerified | Proprietary | Reasoning | 1M | — | Jul 21, 2026 | 62.8 55–70 | 60.6 | 63.5 | 67.6 | 79.5 | 1479 | $0.75 | $3.75 | $1.50✓ | — | ||
| 46 | Muse Spark OpenProvisional | Meta | Open weights | Reasoning | 1M | 822B | Oct 15, 2026 | 62.8 48–77 | — | — | 78.8 | — | — | $1.25 | $4.25 | $2.00 | — | |
| 47 | Qwen3.7 MaxVerified | Alibaba | Proprietary | Reasoning | 1M | — | May 16, 2026 | 62.6 53–72 | 65.5 | 79.0 | 81.4 | 73.1 | 1475 | $1.48 | $4.42 | $2.21 | — | |
| 48 | Claude Opus 4.6Verified | Anthropic | Proprietary | Non-reasoning | 1M | — | Feb 1, 2026 | 62.3 50–75 | 55.0 | 69.1 | 51.2 | 69.8 | 1502 | $5.00 | $25.00 | $10.00✓ | — | |
| 49 | Ornith-1.5-397BProvisional | Ornith AI | Open weights | Reasoning | 262K | — | Aug 18, 2026 | 62.3 48–77 | 66.7 | — | — | 75.6 | — | — | — | — | — | |
| 50 | Gemini 3.5 FlashVerified | Proprietary | Reasoning | 1M | — | May 19, 2026 | 61.9 54–70 | 51.7 | 67.1 | 70.9 | 71.8 | 1482 | $1.50 | $9.00 | $3.38 | — | ||
Speed, latency and end-to-end columns show only our own measurements; a dash means not measured yet.
Page 1 of 5