๐Ÿค Do Chatbot LLMs Talk Too Much?
YapBench Benchmark
Measuring how wordy (lengthโ€‘biased) LLMs are when a short answer would do.
tabularis.ai | Total models: 70 | Last Update: 24 December 2025
{
  • "headers": [
    • "Rank",
    • "model",
    • "YapIndex",
    • "Cat A",
    • "Cat B",
    • "Cat C"
    ],
  • "data": [
    • [
      • "๐Ÿฅ‡",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-3.5-turbo</a>",
      • 22.7,
      • 18,
      • 36,
      • 14
      ],
    • [
      • "๐Ÿฅˆ",
      • "<a target="_blank" href="https://huggingface.co/moonshotai/kimi-k2-0905" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">moonshotai/kimi-k2-0905</a>",
      • 51.3,
      • 85,
      • 41.5,
      • 27.5
      ],
    • [
      • "๐Ÿฅ‰",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-4</a>",
      • 54.8,
      • 44,
      • 28,
      • 92.5
      ],
    • [
      • "4",
      • "<a target="_blank" href="https://huggingface.co/z-ai/glm-4.7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">z-ai/glm-4.7</a>",
      • 73.7,
      • 139,
      • 63,
      • 19
      ],
    • [
      • "5",
      • "<a target="_blank" href="https://x.ai/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">x-ai/grok-4-fast</a>",
      • 77,
      • 55.5,
      • 157.5,
      • 18
      ],
    • [
      • "6",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-4.1-mini</a>",
      • 84.3,
      • 30,
      • 42,
      • 181
      ],
    • [
      • "7",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/o3</a>",
      • 88.5,
      • 96.5,
      • 47,
      • 122
      ],
    • [
      • "8",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5.1-codex</a>",
      • 91.2,
      • 61.5,
      • 41,
      • 171
      ],
    • [
      • "9",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5.2</a>",
      • 94.2,
      • 196.5,
      • 56,
      • 30
      ],
    • [
      • "10",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5.2 (reasoning)</a>",
      • 97.8,
      • 204.5,
      • 51.5,
      • 37.5
      ],
    • [
      • "11",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5</a>",
      • 103.3,
      • 280.5,
      • 8.5,
      • 21
      ],
    • [
      • "12",
      • "<a target="_blank" href="https://x.ai/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">x-ai/grok-4.1-fast</a>",
      • 104.5,
      • 27,
      • 268,
      • 18.5
      ],
    • [
      • "13",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-opus-4.5</a>",
      • 106,
      • 223.5,
      • 54.5,
      • 40
      ],
    • [
      • "14",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-opus-4.5 (reasoning)</a>",
      • 110.3,
      • 237,
      • 54,
      • 40
      ],
    • [
      • "15",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-4.1-nano</a>",
      • 114.2,
      • 54.5,
      • 42.5,
      • 245.5
      ],
    • [
      • "16",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/o4-mini</a>",
      • 119.3,
      • 88,
      • 80,
      • 190
      ],
    • [
      • "17",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5.1</a>",
      • 120,
      • 221.5,
      • 48,
      • 90.5
      ],
    • [
      • "18",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5.1 (reasoning)</a>",
      • 130.8,
      • 230.5,
      • 50,
      • 112
      ],
    • [
      • "19",
      • "<a target="_blank" href="https://x.ai/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">x-ai/grok-4</a>",
      • 132.7,
      • 129,
      • 250,
      • 19
      ],
    • [
      • "20",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/o3-mini</a>",
      • 153.7,
      • 142,
      • 160.5,
      • 158.5
      ],
    • [
      • "21",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-4o</a>",
      • 174.3,
      • 57.5,
      • 48.5,
      • 417
      ],
    • [
      • "22",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5-nano</a>",
      • 179.5,
      • 365.5,
      • 82.5,
      • 90.5
      ],
    • [
      • "23",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-4.1</a>",
      • 186.8,
      • 95,
      • 87.5,
      • 378
      ],
    • [
      • "24",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-4o-mini</a>",
      • 192,
      • 72.5,
      • 104.5,
      • 399
      ],
    • [
      • "25",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-2.5-flash (reasoning)</a>",
      • 207.2,
      • 354.5,
      • 72.5,
      • 194.5
      ],
    • [
      • "26",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-3.5-sonnet</a>",
      • 209.2,
      • 132.5,
      • 180.5,
      • 314.5
      ],
    • [
      • "27",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-oss-20b</a>",
      • 213.2,
      • 110.5,
      • 71,
      • 458
      ],
    • [
      • "28",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-2.5-flash</a>",
      • 225,
      • 505.5,
      • 46.5,
      • 123
      ],
    • [
      • "29",
      • "<a target="_blank" href="https://www.deepseek.com/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">deepseek/deepseek-v3.2 (reasoning)</a>",
      • 226.5,
      • 124,
      • 329.5,
      • 226
      ],
    • [
      • "30",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-2.0-flash-lite-001</a>",
      • 242.8,
      • 139,
      • 44.5,
      • 545
      ],
    • [
      • "31",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-3-pro-preview</a>",
      • 247.8,
      • 358,
      • 94,
      • 291.5
      ],
    • [
      • "32",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-5-mini</a>",
      • 254.7,
      • 422.5,
      • 105,
      • 236.5
      ],
    • [
      • "33",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-4-turbo</a>",
      • 260.5,
      • 78.5,
      • 63,
      • 640
      ],
    • [
      • "34",
      • "<a target="_blank" href="https://huggingface.co/allenai/olmo-2-0325-32b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">allenai/olmo-2-0325-32b-instruct</a>",
      • 269,
      • 620.5,
      • 164.5,
      • 22
      ],
    • [
      • "35",
      • "<a target="_blank" href="https://huggingface.co/Qwen" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">qwen/qwen3-235b-a22b-2507 (reasoning)</a>",
      • 283.3,
      • 131,
      • 130,
      • 589
      ],
    • [
      • "36",
      • "<a target="_blank" href="https://huggingface.co/Qwen" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">qwen/qwen-plus</a>",
      • 285.2,
      • 124,
      • 123.5,
      • 608
      ],
    • [
      • "37",
      • "<a target="_blank" href="https://huggingface.co/Qwen" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">qwen/qwen3-235b-a22b-2507</a>",
      • 286.8,
      • 138,
      • 140.5,
      • 582
      ],
    • [
      • "38",
      • "<a target="_blank" href="https://platform.openai.com/docs/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openai/gpt-oss-120b</a>",
      • 289.2,
      • 142,
      • 142,
      • 583.5
      ],
    • [
      • "39",
      • "<a target="_blank" href="https://huggingface.co/microsoft/phi-4-reasoning-plus" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">microsoft/phi-4-reasoning-plus</a>",
      • 290.5,
      • 210,
      • 187.5,
      • 474
      ],
    • [
      • "40",
      • "<a target="_blank" href="https://x.ai/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">x-ai/grok-code-fast-1</a>",
      • 293.3,
      • 137.5,
      • 476.5,
      • 266
      ],
    • [
      • "41",
      • "<a target="_blank" href="https://huggingface.co/microsoft/phi-4-reasoning-plus (reasoning)" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">microsoft/phi-4-reasoning-plus (reasoning)</a>",
      • 295.3,
      • 207,
      • 184.5,
      • 494.5
      ],
    • [
      • "42",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-2.5-flash-lite (reasoning)</a>",
      • 301,
      • 188,
      • 51.5,
      • 663.5
      ],
    • [
      • "43",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-sonnet-4.5 (reasoning)</a>",
      • 302.7,
      • 298.5,
      • 132.5,
      • 477
      ],
    • [
      • "44",
      • "<a target="_blank" href="https://huggingface.co/minimax/minimax-m2" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">minimax/minimax-m2</a>",
      • 310.3,
      • 138.5,
      • 400.5,
      • 392
      ],
    • [
      • "45",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-sonnet-4.5</a>",
      • 310.8,
      • 295.5,
      • 132,
      • 505
      ],
    • [
      • "46",
      • "<a target="_blank" href="https://huggingface.co/meta-llama/llama-3.3-70b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/llama-3.3-70b-instruct</a>",
      • 330.8,
      • 164,
      • 127,
      • 701.5
      ],
    • [
      • "47",
      • "<a target="_blank" href="https://huggingface.co/meta-llama/llama-3.1-8b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/llama-3.1-8b-instruct</a>",
      • 331.8,
      • 137,
      • 96.5,
      • 762
      ],
    • [
      • "48",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-2.0-flash-001</a>",
      • 357.7,
      • 291,
      • 43,
      • 739
      ],
    • [
      • "49",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-haiku-4.5</a>",
      • 365,
      • 248,
      • 129,
      • 718
      ],
    • [
      • "50",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-haiku-4.5 (reasoning)</a>",
      • 365.2,
      • 248,
      • 129,
      • 718.5
      ],
    • [
      • "51",
      • "<a target="_blank" href="https://www.deepseek.com/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">deepseek/deepseek-chat</a>",
      • 366.5,
      • 145.5,
      • 333.5,
      • 620.5
      ],
    • [
      • "52",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-3-flash-preview</a>",
      • 370.2,
      • 447.5,
      • 131.5,
      • 531.5
      ],
    • [
      • "53",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-3-flash-preview (reasoning)</a>",
      • 376,
      • 430,
      • 126.5,
      • 571.5
      ],
    • [
      • "54",
      • "<a target="_blank" href="https://docs.mistral.ai/getting-started/models/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/mistral-medium-3</a>",
      • 388.2,
      • 143,
      • 404.5,
      • 617
      ],
    • [
      • "55",
      • "<a target="_blank" href="https://docs.mistral.ai/getting-started/models/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/mistral-small-3.1-24b-instruct</a>",
      • 402.5,
      • 190,
      • 217,
      • 800.5
      ],
    • [
      • "56",
      • "<a target="_blank" href="https://docs.anthropic.com/en/docs/models-overview" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">anthropic/claude-3.5-haiku</a>",
      • 427.2,
      • 168,
      • 280.5,
      • 833
      ],
    • [
      • "57",
      • "<a target="_blank" href="https://huggingface.co/z-ai/glm-4.6v" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">z-ai/glm-4.6v</a>",
      • 431.2,
      • 196,
      • 147,
      • 950.5
      ],
    • [
      • "58",
      • "<a target="_blank" href="https://www.deepseek.com/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">deepseek/deepseek-v3.2</a>",
      • 461.2,
      • 240,
      • 317,
      • 826.5
      ],
    • [
      • "59",
      • "<a target="_blank" href="https://docs.mistral.ai/getting-started/models/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/mistral-large-2512</a>",
      • 476.3,
      • 436.5,
      • 379.5,
      • 613
      ],
    • [
      • "60",
      • "<a target="_blank" href="https://docs.mistral.ai/getting-started/models/" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/devstral-2512</a>",
      • 483.5,
      • 373.5,
      • 467.5,
      • 609.5
      ],
    • [
      • "61",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-2.5-flash-lite</a>",
      • 519.5,
      • 478,
      • 47,
      • 1033.5
      ],
    • [
      • "62",
      • "<a target="_blank" href="https://huggingface.co/allenai/olmo-3.1-32b-think:free" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">allenai/olmo-3.1-32b-think:free</a>",
      • 568.2,
      • 174,
      • 620,
      • 910.5
      ],
    • [
      • "63",
      • "<a target="_blank" href="https://ai.google.dev/models" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemini-2.5-pro</a>",
      • 580,
      • 415,
      • 199.5,
      • 1125.5
      ],
    • [
      • "64",
      • "<a target="_blank" href="https://huggingface.co/Qwen" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">qwen/qwen3-vl-235b-a22b-thinking</a>",
      • 647.7,
      • 214.5,
      • 890,
      • 838.5
      ],
    • [
      • "65",
      • "<a target="_blank" href="https://huggingface.co/Qwen" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">qwen/qwen3-32b</a>",
      • 780.3,
      • 205,
      • 851,
      • 1285
      ],
    • [
      • "66",
      • "<a target="_blank" href="https://huggingface.co/amazon/nova-2-lite-v1 (reasoning)" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">amazon/nova-2-lite-v1 (reasoning)</a>",
      • 872.5,
      • 1297,
      • 233,
      • 1087.5
      ],
    • [
      • "67",
      • "<a target="_blank" href="https://huggingface.co/Qwen" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">qwen/qwen-plus (reasoning)</a>",
      • 878.2,
      • 273.5,
      • 1233.5,
      • 1127.5
      ],
    • [
      • "68",
      • "<a target="_blank" href="https://huggingface.co/amazon/nova-2-lite-v1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">amazon/nova-2-lite-v1</a>",
      • 957.5,
      • 579,
      • 602,
      • 1691.5
      ],
    • [
      • "69",
      • "<a target="_blank" href="https://huggingface.co/z-ai/glm-4.6:exacto" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">z-ai/glm-4.6:exacto</a>",
      • 984.5,
      • 1118.5,
      • 426.5,
      • 1408.5
      ],
    • [
      • "70",
      • "<a target="_blank" href="https://huggingface.co/z-ai/glm-4.5" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">z-ai/glm-4.5</a>",
      • 1535.8,
      • 1297.5,
      • 1014.5,
      • 2295.5
      ]
    ],
  • "metadata": null
}