# November 2026 rankings

In the November 2026 rankings release, Claude Fable 5.2 is #1 Overall at 91.41 (Estimated), out of 214 models ranked. By board, Claude Fable 5.2 is #1 on the Overall, Coding, Reasoning, Agentic, Knowledge and Multimodal boards; Claude Opus 4.8 is #1 on the Math board. The Token Price Index stood at 15 for November 2026 (March 2023 = 100). The release was frozen on November 12, 2026 from commit 04172aa27, so it will not change.

Supported means we have enough independent evidence to stand behind the row. Estimated means the rank is visible and the uncertainty is wider.

## Overall

214 models ranked. Today's board: https://benchlm.ai/

| Rank | Model | Lab | Score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://benchlm.ai/models/claude-fable-5-2) | Anthropic | 91.41 | Estimated |
| 2 | [Gemini 4 Carbon](https://benchlm.ai/models/gemini-4-carbon) | Google | 87.91 | Supported |
| 3 | [Claude Opus 5.5](https://benchlm.ai/models/claude-opus-5-5) | Anthropic | 85.77 | Supported |
| 4 | [GPT-6 Astra](https://benchlm.ai/models/gpt-6-astra) | OpenAI | 84.98 | Supported |
| 5 | [GPT-6.1 Sol](https://benchlm.ai/models/gpt-6-1-sol) | OpenAI | 84.91 | Supported |
| 6 | [Gemini 4 Argon](https://benchlm.ai/models/gemini-4-argon) | Google | 81.38 | Supported |
| 7 | [Claude Sonnet 5.5](https://benchlm.ai/models/claude-sonnet-5-5) | Anthropic | 81.24 | Supported |
| 8 | [Claude Fable 5.1](https://benchlm.ai/models/claude-fable-5-1) | Anthropic | 80.82 | Supported |
| 9 | [Claude Fable 5](https://benchlm.ai/models/claude-fable) | Anthropic | 80.38 | Supported |
| 10 | [GPT-6.1 Terra](https://benchlm.ai/models/gpt-6-1-terra) | OpenAI | 80.13 | Estimated |

## Coding

158 models ranked. Today's board: https://benchlm.ai/coding

| Rank | Model | Lab | Score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://benchlm.ai/models/claude-fable-5-2) | Anthropic | 86.31 | Estimated |
| 2 | [Claude Opus 5.5](https://benchlm.ai/models/claude-opus-5-5) | Anthropic | 82.4 | Supported |
| 3 | [Claude Sonnet 5.5](https://benchlm.ai/models/claude-sonnet-5-5) | Anthropic | 81.41 | Supported |
| 4 | [Gemini 4 Carbon](https://benchlm.ai/models/gemini-4-carbon) | Google | 80.52 | Estimated |
| 5 | [Claude Fable 5.1](https://benchlm.ai/models/claude-fable-5-1) | Anthropic | 76.34 | Supported |
| 6 | [GPT-6 Astra](https://benchlm.ai/models/gpt-6-astra) | OpenAI | 73.91 | Supported |
| 7 | [Gemini 4 Argon](https://benchlm.ai/models/gemini-4-argon) | Google | 71.95 | Supported |
| 8 | [Claude Fable 5](https://benchlm.ai/models/claude-fable) | Anthropic | 70.97 | Supported |
| 9 | [Muse Wonder Full](https://benchlm.ai/models/muse-wonder-full) | Meta | 70.79 | Supported |
| 10 | [Claude Opus 5](https://benchlm.ai/models/claude-opus-5) | Anthropic | 70.3 | Supported |

## Reasoning

158 models ranked. Today's board: https://benchlm.ai/reasoning

| Rank | Model | Lab | Score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://benchlm.ai/models/claude-fable-5-2) | Anthropic | 89.93 | Supported |
| 2 | [Gemini 4 Carbon](https://benchlm.ai/models/gemini-4-carbon) | Google | 83.37 | Supported |
| 3 | [GPT-6 Astra](https://benchlm.ai/models/gpt-6-astra) | OpenAI | 80.43 | Supported |
| 4 | [Claude Opus 5.5](https://benchlm.ai/models/claude-opus-5-5) | Anthropic | 79.95 | Supported |
| 5 | [GPT-6.1 Sol](https://benchlm.ai/models/gpt-6-1-sol) | OpenAI | 79.94 | Supported |
| 6 | [Gemini 4 Argon](https://benchlm.ai/models/gemini-4-argon) | Google | 77.32 | Supported |
| 7 | [Claude Fable 5.1](https://benchlm.ai/models/claude-fable-5-1) | Anthropic | 76.78 | Supported |
| 8 | [Claude Sonnet 5.5](https://benchlm.ai/models/claude-sonnet-5-5) | Anthropic | 76.1 | Supported |
| 9 | [Muse Wonder Full](https://benchlm.ai/models/muse-wonder-full) | Meta | 75.88 | Supported |
| 10 | [GPT-6.1 Terra](https://benchlm.ai/models/gpt-6-1-terra) | OpenAI | 75.3 | Supported |

## Agentic

132 models ranked. Today's board: https://benchlm.ai/agentic

| Rank | Model | Lab | Score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://benchlm.ai/models/claude-fable-5-2) | Anthropic | 90.06 | Estimated |
| 2 | [Claude Opus 5.5](https://benchlm.ai/models/claude-opus-5-5) | Anthropic | 89.34 | Supported |
| 3 | [Claude Fable 5.1](https://benchlm.ai/models/claude-fable-5-1) | Anthropic | 80.35 | Supported |
| 4 | [Gemini 4 Argon](https://benchlm.ai/models/gemini-4-argon) | Google | 77.59 | Supported |
| 5 | [Claude Opus 5](https://benchlm.ai/models/claude-opus-5) | Anthropic | 76.98 | Supported |
| 6 | [GPT-6.1 Terra](https://benchlm.ai/models/gpt-6-1-terra) | OpenAI | 76.01 | Estimated |
| 7 | [GPT-6.1 Sol](https://benchlm.ai/models/gpt-6-1-sol) | OpenAI | 75.56 | Estimated |
| 8 | [Claude Fable 5](https://benchlm.ai/models/claude-fable) | Anthropic | 74.02 | Supported |
| 9 | [GPT-6 Astra](https://benchlm.ai/models/gpt-6-astra) | OpenAI | 73.52 | Supported |
| 10 | [Kimi K3.1 Pro](https://benchlm.ai/models/kimi-3-1-pro) | Moonshot AI | 72.72 | Supported |

## Knowledge

179 models ranked. Today's board: https://benchlm.ai/knowledge

| Rank | Model | Lab | Score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://benchlm.ai/models/claude-fable-5-2) | Anthropic | 97.41 | Supported |
| 2 | [Claude Opus 5.5](https://benchlm.ai/models/claude-opus-5-5) | Anthropic | 88.17 | Supported |
| 3 | [Claude Fable 5.1](https://benchlm.ai/models/claude-fable-5-1) | Anthropic | 84.7 | Supported |
| 4 | [GPT-6.1 Sol](https://benchlm.ai/models/gpt-6-1-sol) | OpenAI | 84.13 | Supported |
| 5 | [GPT-6 Astra](https://benchlm.ai/models/gpt-6-astra) | OpenAI | 83.81 | Supported |
| 6 | [Claude Opus 5](https://benchlm.ai/models/claude-opus-5) | Anthropic | 80.31 | Supported |
| 7 | [Claude Fable 5](https://benchlm.ai/models/claude-fable) | Anthropic | 80.16 | Supported |
| 8 | [Claude Sonnet 5.5](https://benchlm.ai/models/claude-sonnet-5-5) | Anthropic | 79.9 | Supported |
| 9 | [Gemini 4 Argon](https://benchlm.ai/models/gemini-4-argon) | Google | 79.36 | Supported |
| 10 | [GPT-6 Sol](https://benchlm.ai/models/gpt-6-sol) | OpenAI | 78.67 | Estimated |

## Multimodal (preliminary)

67 models ranked. Today's board: https://benchlm.ai/multimodal-grounded

This board is preliminary: its roster is still thin, so it issues no badges yet.

| Rank | Model | Lab | Score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://benchlm.ai/models/claude-fable-5-2) | Anthropic | 89.35 | Estimated |
| 2 | [Claude Opus 5.5](https://benchlm.ai/models/claude-opus-5-5) | Anthropic | 84.44 | Supported |
| 3 | [Claude Fable 5.1](https://benchlm.ai/models/claude-fable-5-1) | Anthropic | 81.2 | Estimated |
| 4 | [GPT-6 Astra](https://benchlm.ai/models/gpt-6-astra) | OpenAI | 78.93 | Supported |
| 5 | [GPT-6.1 Sol](https://benchlm.ai/models/gpt-6-1-sol) | OpenAI | 78.36 | Supported |
| 6 | [Claude Opus 5](https://benchlm.ai/models/claude-opus-5) | Anthropic | 77.78 | Estimated |
| 7 | [Claude Sonnet 5.5](https://benchlm.ai/models/claude-sonnet-5-5) | Anthropic | 77.65 | Estimated |
| 8 | [GPT-6.1 Terra](https://benchlm.ai/models/gpt-6-1-terra) | OpenAI | 77.22 | Supported |
| 9 | [GPT-5.6 Sol](https://benchlm.ai/models/gpt-5-6-sol) | OpenAI | 75.48 | Supported |
| 10 | [Claude Fable 5](https://benchlm.ai/models/claude-fable) | Anthropic | 75.26 | Supported |

## Math

12 models ranked. Today's board: https://benchlm.ai/math

This board still uses the legacy weighted category score, so its rows carry no Supported label and issue no badges.

| Rank | Model | Lab | Score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 4.8](https://benchlm.ai/models/claude-opus-4-8) | Anthropic | 79.3 | Estimated |
| 2 | [Qwen3.7 Max](https://benchlm.ai/models/qwen3-7-max) | Alibaba | 78.3 | Estimated |
| 3 | [GLM-5.2](https://benchlm.ai/models/glm-5-2) | Z.AI | 74.6 | Estimated |
| 4 | [Kimi K2.6](https://benchlm.ai/models/kimi-2-6) | Moonshot AI | 73.2 | Estimated |
| 5 | [Inkling-Small](https://benchlm.ai/models/inkling-small) | Thinking Machines Lab | 64.6 | Estimated |
| 6 | [Qwen3.6 Plus](https://benchlm.ai/models/qwen3-6-plus) | Alibaba | 62.3 | Estimated |
| 7 | [Qwen3.6-27B](https://benchlm.ai/models/qwen3-6-27b) | Alibaba | 56.2 | Estimated |
| 8 | [GLM-5.1](https://benchlm.ai/models/glm-5-1) | Z.AI | 55.7 | Estimated |
| 9 | [Inkling](https://benchlm.ai/models/inkling) | Thinking Machines Lab | 54.6 | Estimated |
| 10 | [Claude Opus 4.5](https://benchlm.ai/models/claude-opus-4-5) | Anthropic | 52.9 | Estimated |

## Cite this release

BenchLM.ai, "November 2026 rankings", https://benchlm.ai/monthly-rankings/2026-11, frozen November 12, 2026.

```bibtex
@misc{benchlm_release_2026_11,
  author = {{BenchLM.ai}},
  title = {{BenchLM monthly rankings: November 2026}},
  year = {2026},
  month = {11},
  url = {https://benchlm.ai/monthly-rankings/2026-11},
  note = {Frozen 2026-11-12 from commit 04172aa27}
}
```

## Badges

Models with a Supported top-10 rank on a board that issues badges can show a rank badge: https://benchlm.ai/badges

## How this release is made

- Frozen on November 12, 2026 from commit 04172aa27. The ranks come from the same method as the live boards: https://benchlm.ai/methodology
- Corrections are listed on the release, never edited silently.
- The next release comes out early next month.
- No payment changes a score, a rank or a label. https://benchlm.ai/editorial-policy#commercial-independence

Canonical page: https://benchlm.ai/monthly-rankings/2026-11