TensorFeed Intelligence Index, November 2026
In progressAs of November 1, 2026, with the month in progress, Claude Opus 5.5 (Anthropic) leads the TensorFeed Intelligence Index for November 2026 with a score of 97.1, among the 18 models ranked on the 2026 benchmark set. Claude Sonnet 5.5 (93.7) and Claude Fable 5.1 (89.9) follow.
Updated daily; latest run . Methodology 1.4. 18 models ranked on the 2026 benchmark set, 29 on the 2024 set, ranked separately. The record freezes at the last daily run of November 2026.
Ranking, 2026 benchmark set
Terminal-Bench 4.0, FrontierCode, OSWorld 2.0, BrowseComp, and Humanity's Last Exam with tools. Change is against October 2026.
| Rank | Model | Provider | TFII | Change |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 97.1 | same |
| 2 | Claude Sonnet 5.5 | Anthropic | 93.7 | same |
| 3 | Claude Fable 5.1 | Anthropic | 89.9 | same |
| 4 | Claude Opus 5 | Anthropic | 83.9 | same |
| 5 | GPT-6 Astra | OpenAI | 83.3 | same |
| 6 | Claude Fable 5 | Anthropic | 81.6 | same |
| 7 | GPT-5.6 Sol | OpenAI | 74.5 | same |
| 8 | GLM-5.3 | Z.ai | 71.8 | same |
| 9 | Claude Haiku 5.5 | Anthropic | 69.7 | same |
| 10 | Claude Opus 4.8 | Anthropic | 67.9 | same |
| 11 | Kimi K3 | Moonshot AI | 65.1 | same |
| 12 | GLM-5.3 Flash | Z.ai | 62.8 | same |
| 13 | GPT-5.6 Terra | OpenAI | 60.9 | same |
| 14 | Claude Sonnet 5 | Anthropic | 59.2 | same |
| 15 | GPT-5.6 Luna | OpenAI | 53.2 | same |
| 16 | Gemini 3.7 Flash | 52.3 | same | |
| 17 | Inkling | Thinking Machines | 35.7 | same |
| 18 | MiniMax M3 | MiniMax | 29.8 | same |
Ranked separately: 29 models scored only on the 2024 benchmark set
MMLU-Pro, HumanEval, GPQA Diamond, MATH, and SWE-bench Verified. These scores are not comparable with the 2026 set above.
- 1. Grok 4.6 (xAI)83.2
- 2. Grok 4.5 (xAI)80.0
- 3. Gemini 3.8 Flash (Google)79.0
- 4. Gemini 3.6 Flash (Google)78.1
- 5. Muse Spark 1.1 (Meta)78.1
- 6. Gemini 3.5 Flash (Google)77.8
- 7. Qwen3.8-Max (Alibaba)77.4
- 8. GLM-5.2 (Z.ai)75.6
- 9. Qwen3.8 27B (Alibaba)75.2
- 10. Gemini 3.5 Flash-Lite (Google)73.3
- 11. GPT-5.5 (OpenAI)69.8
- 12. Claude Opus 4.7 (Anthropic)69.8
- 13. DeepSeek V4 Pro (DeepSeek)69.1
- 14. Claude Opus 4.6 (Anthropic)67.8
- 15. Claude Sonnet 4.6 (Anthropic)64.6
- 16. Gemini 2.5 Pro (Google)64.3
- 17. o1 (OpenAI)62.8
- 18. DeepSeek V4 Flash (DeepSeek)62.1
- 19. Llama 4 Scout (Meta)61.8
- 20. Gemini 2.0 Flash (Google)60.7
- 21. GPT-4.5 (OpenAI)59.5
- 22. o3-mini (OpenAI)58.6
- 23. Claude Haiku 4.5 (Anthropic)58.5
- 24. DeepSeek V3 (DeepSeek)58.4
- 25. Mistral Large (Mistral)57.2
- 26. Nemotron 3.5 Lightning (NVIDIA)56.7
- 27. Llama 4 Maverick (Meta)56.1
- 28. GPT-4o (OpenAI)55.6
- 29. Mistral Small (Mistral)55.3
Cite this record
TensorFeed Intelligence Index, November 2026 (in progress, as of November 1, 2026; methodology 1.4). https://tensorfeed.ai/intelligence/2026-11
Machine-readable: https://tensorfeed.ai/api/intelligence/monthly/2026-11. A model's live rank is also available as an embeddable badge.
How the index is built, and why the 2024 and 2026 sets are never compared: TensorFeed Intelligence Index methodology.