# NYT Connections leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-nyt-connections

NYT Connections LLM Benchmark (extended version). Every model the catalog carries a published NYT Connections value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Sort 16 to 20 words into four groups of four, one attempt per puzzle, no feedback |
| Tasks | 940 NYT Connections puzzles, each with up to four added trick words |
| Difficulty | Wordplay, word knowledge and decoys that fit almost-but-not-quite |
| Published by | [NYT Connections LLM Benchmark (Lech Mazur, GitHub)](https://github.com/lechmazur/nyt-connections) |

Lech Mazur's NYT Connections benchmark gives a model 940 puzzles from the New York Times word game, each with up to four extra trick words, and asks it to sort the words into four groups of four in one try. It tests word knowledge, wordplay and resisting plausible decoys.

## NYT Connections ranking

94 models with a published NYT Connections value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Sort 16 to 20 words into four groups of four, one attempt per puzzle, no feedback | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 4 Carbon](https://modelchoice.dev/models/gemini-4-carbon) | Google | 99.3 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 4 Argon](https://modelchoice.dev/models/gemini-4-argon) | Google | 98.6 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 98.4 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 97.8 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 97.4 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 97.4 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Fable 5.2](https://modelchoice.dev/models/claude-fable-5-2) | Anthropic | 97.3 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 96.2 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Gemini 3 Pro](https://modelchoice.dev/models/gemini-3-pro) | Google | 94.4 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 94.3 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Gemini 3.7 Flash](https://modelchoice.dev/models/gemini-3-7-flash) | Google | 94.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 93.8 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 93.6 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 93.4 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Muse Wonder](https://modelchoice.dev/models/muse-wonder) | Meta | 93.4 | Observed 2026-11-21 · source benchlm:models |
| 16 | [DeepSeek V4.1 Flash 1017](https://modelchoice.dev/models/deepseek-v4-1-flash) | DeepSeek | 92.8 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Fable 5](https://modelchoice.dev/models/claude-fable-5) | Anthropic | 92.7 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 92.6 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Claude Opus 4.6 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-6-thinking) | Anthropic | 92.1 | Observed 2026-11-21 · source benchlm:models |
| 20 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 91.3 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 91.1 | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 90.1 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 90.0 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Grok 4.20 Multi-agent](https://modelchoice.dev/models/grok-4-20-multi-agent-beta) | xAI | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Gemini 3.6 Flash](https://modelchoice.dev/models/gemini-3-6-flash) | Google | 89.0 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 88.5 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Qwen3.8 Max](https://modelchoice.dev/models/qwen3-8-max) | Alibaba | 88.3 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Grok 4.1 Fast (Reasoning)](https://modelchoice.dev/models/grok-4-1-fast-reasoning) | xAI | 87.4 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 87.2 | Observed 2026-11-21 · source benchlm:models |
| 30 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 86.8 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Grok 4.20](https://modelchoice.dev/models/grok-4-20-beta) | xAI | 85.4 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Muse Spark 1.3](https://modelchoice.dev/models/muse-spark-1-3) | Meta | 85.1 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 85.1 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 84.9 | Observed 2026-11-21 · source benchlm:models |
| 35 | [GPT-5.2](https://modelchoice.dev/models/gpt-5-2) | OpenAI | 83.6 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Hy4](https://modelchoice.dev/models/hy4) | Tencent | 83.5 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Gemini 3 Flash](https://modelchoice.dev/models/gemini-3-flash) | Google | 83.1 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Grok 4.6](https://modelchoice.dev/models/grok-4-6) | xAI | 80.0 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Grok 4.5](https://modelchoice.dev/models/grok-4-5) | xAI | 79.9 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Muse Spark 1.2](https://modelchoice.dev/models/muse-spark-1-2) | Meta | 79.2 | Observed 2026-11-21 · source benchlm:models |
| 42 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Muse Spark Open](https://modelchoice.dev/models/muse-spark-open) | Meta | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 44 | [GLM-5.1](https://modelchoice.dev/models/glm-5-1) | Z.AI | 77.7 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Grok 4.7](https://modelchoice.dev/models/grok-4-7) | xAI | 76.8 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Step 5 Preview](https://modelchoice.dev/models/step-5-preview) | StepFun | 76.6 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 75.1 | Observed 2026-11-21 · source benchlm:models |
| 48 | [GLM-5 (Reasoning)](https://modelchoice.dev/models/glm-5-reasoning) | Z.AI | 74.8 | Last good 2026-11-18 · source benchlm:models |
| 48 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 74.8 | Observed 2026-11-21 · source benchlm:models |
| 50 | [GLM-5.2](https://modelchoice.dev/models/glm-5-2) | Z.AI | 74.3 | Observed 2026-11-21 · source benchlm:models |
| 51 | [GLM-5.3](https://modelchoice.dev/models/glm-5-3) | Z.AI | 74.2 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Qwen 3.6 Max (preview)](https://modelchoice.dev/models/qwen3-6-max-preview) | Alibaba | 74.1 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Gemma 4 31B](https://modelchoice.dev/models/gemma-4-31b) | Google | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Kimi K2.5 (Reasoning)](https://modelchoice.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 69.9 | Last good 2026-11-18 · source benchlm:models |
| 55 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 69.4 | Observed 2026-11-21 · source benchlm:models |
| 56 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 68.7 | Observed 2026-11-21 · source benchlm:models |
| 57 | [Hy4 preview](https://modelchoice.dev/models/hy4-preview) | Tencent | 68.2 | Observed 2026-11-21 · source benchlm:models |
| 58 | [Claude Haiku 5.5](https://modelchoice.dev/models/claude-haiku-5-5) | Anthropic | 65.7 | Observed 2026-11-21 · source benchlm:models |
| 59 | [MiniMax M3](https://modelchoice.dev/models/minimax-m3) | MiniMax | 65.1 | Observed 2026-11-21 · source benchlm:models |
| 60 | [GPT-5.4 mini](https://modelchoice.dev/models/gpt-5-4-mini) | OpenAI | 61.8 | Observed 2026-11-21 · source benchlm:models |
| 61 | [Gemini 3.5 Flash-Lite](https://modelchoice.dev/models/gemini-3-5-flash-lite) | Google | 60.4 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 60.3 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Qwen3.5 397B (Reasoning)](https://modelchoice.dev/models/qwen3-5-397b-reasoning) | Alibaba | 58.9 | Last good 2026-11-18 · source benchlm:models |
| 64 | [Grok 4.3](https://modelchoice.dev/models/grok-4-3) | xAI | 55.2 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Qwen3.8-27B](https://modelchoice.dev/models/qwen3-8-27b) | Alibaba | 54.5 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Claude Opus 4.5 Thinking](https://modelchoice.dev/models/claude-opus-4-5-thinking) | Anthropic | 52.5 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Qwen3.5-122B-A10B](https://modelchoice.dev/models/qwen3-5-122b-a10b) | Alibaba | 51.7 | Observed 2026-11-21 · source benchlm:models |
| 68 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 49.4 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Qwen3.5-27B](https://modelchoice.dev/models/qwen3-5-27b) | Alibaba | 47.9 | Observed 2026-11-21 · source benchlm:models |
| 70 | [Claude Sonnet 4.6](https://modelchoice.dev/models/claude-sonnet-4-6) | Anthropic | 44.8 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Qwen3.7 Flash](https://modelchoice.dev/models/qwen3-7-flash) | Alibaba | 43.8 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Claude Opus 4.6](https://modelchoice.dev/models/claude-opus-4-6) | Anthropic | 43.2 | Observed 2026-11-21 · source benchlm:models |
| 73 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 41.6 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Hy3](https://modelchoice.dev/models/hy3) | Tencent | 41.2 | Observed 2026-11-21 · source benchlm:models |
| 75 | [Step 3.7 Flash](https://modelchoice.dev/models/step-3-7-flash) | StepFun | 39.7 | Observed 2026-11-21 · source benchlm:models |
| 76 | [Claude Opus 4.7 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-7-max) | Anthropic | 39.0 | Last good 2026-11-18 · source benchlm:models |
| 77 | [Claude Sonnet 4.5 Thinking](https://modelchoice.dev/models/claude-sonnet-4-5-thinking) | Anthropic | 37.3 | Observed 2026-11-21 · source benchlm:models |
| 78 | [DeepSeek V3.2 (Thinking)](https://modelchoice.dev/models/deepseek-v3-2-thinking) | DeepSeek | 36.7 | Last good 2026-11-18 · source benchlm:models |
| 79 | [Claude Sonnet 4.5](https://modelchoice.dev/models/claude-sonnet-4-5) | Anthropic | 35.8 | Observed 2026-11-21 · source benchlm:models |
| 80 | [MiMo-V2.5-Pro](https://modelchoice.dev/models/mimo-v2-5-pro) | Xiaomi | 34.4 | Observed 2026-11-21 · source benchlm:models |
| 81 | [MiniMax M3.1 Flash](https://modelchoice.dev/models/minimax-m3-1-flash) | MiniMax | 28.3 | Observed 2026-11-21 · source benchlm:models |
| 82 | [Mistral Large 4](https://modelchoice.dev/models/mistral-large-4) | Mistral | 27.4 | Observed 2026-11-21 · source benchlm:models |
| 83 | [MiMo-V2-Pro](https://modelchoice.dev/models/mimo-v2-pro) | Xiaomi | 25.8 | Observed 2026-11-21 · source benchlm:models |
| 84 | [MiniMax M2.7](https://modelchoice.dev/models/minimax-m2-7) | MiniMax | 24.7 | Observed 2026-11-21 · source benchlm:models |
| 85 | [Hy3 Preview](https://modelchoice.dev/models/hy3-preview) | Tencent | 17.2 | Observed 2026-11-21 · source benchlm:models |
| 86 | [Trinity-Large-Thinking](https://modelchoice.dev/models/trinity-large-thinking) | Arcee AI | 16.5 | Observed 2026-11-21 · source benchlm:models |
| 87 | [Claude Haiku 4.5](https://modelchoice.dev/models/claude-haiku-4-5) | Anthropic | 14.3 | Observed 2026-11-21 · source benchlm:models |
| 88 | [Mistral Medium 3.5 128B](https://modelchoice.dev/models/mistral-medium-3-5-128b) | Mistral | 12.9 | Observed 2026-11-21 · source benchlm:models |
| 89 | [Grok 4.1 Fast](https://modelchoice.dev/models/grok-4-1-fast) | xAI | 12.3 | Observed 2026-11-21 · source benchlm:models |
| 90 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 10.8 | Last good 2026-11-18 · source benchlm:models |
| 91 | [DeepSeek V3.2](https://modelchoice.dev/models/deepseek-v3-2) | DeepSeek | 8.2 | Observed 2026-11-21 · source benchlm:models |
| 91 | [Gemini 3.1 Flash-Lite](https://modelchoice.dev/models/gemini-3-1-flash-lite) | Google | 8.2 | Observed 2026-11-21 · source benchlm:models |
| 93 | [Llama 4 Maverick](https://modelchoice.dev/models/llama-4-maverick) | Meta | 8.0 | Observed 2026-11-21 · source benchlm:models |
| 94 | [Mistral Large 3](https://modelchoice.dev/models/mistral-large-3) | Mistral | 7.5 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
