# HLE leaderboard

Knowledge 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/knowledge-hle

Humanity's Last Exam. Every model the catalog carries a published HLE value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Open-ended and multiple choice |
| Tasks | Expert-level questions |
| Difficulty | Frontier expert level |
| Published by | [Humanity's Last Exam](https://lastexam.ai/) |

An expert-authored benchmark designed to probe frontier knowledge and reasoning. BenchLM keeps protocol differences visible because tool-assisted and closed-book HLE runs answer different questions.

## HLE ranking

82 models with a published HLE 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 | Open-ended and multiple choice | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://modelchoice.dev/models/claude-fable-5-2) | Anthropic | 74.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 70 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 67.7 | Last good 2026-09-22 · source benchlm:models |
| 4 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 65 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 64.7 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Mythos 5](https://modelchoice.dev/models/claude-mythos-5) | Anthropic | 64.5 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 62.1 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Hy4](https://modelchoice.dev/models/hy4) | Tencent | 59.1 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-5.4 Pro](https://modelchoice.dev/models/gpt-5-4-pro) | OpenAI | 58.7 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 57.9 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 57.4 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-5.5 Pro](https://modelchoice.dev/models/gpt-5-5-pro) | OpenAI | 57.2 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Apodex 1.1](https://modelchoice.dev/models/apodex-1-1) | Apodex | 56.1 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 56 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Hy4 preview](https://modelchoice.dev/models/hy4-preview) | Tencent | 55.4 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Hy4 flash](https://modelchoice.dev/models/hy4-flash) | Tencent | 55.2 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 54.7 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Opus 4.7 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-7-max) | Anthropic | 54.7 | Last good 2026-11-18 · source benchlm:models |
| 19 | [Inkling 2 Small](https://modelchoice.dev/models/inkling-2-small) | Thinking Machines Lab | 53.2 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Claude Opus 4.6](https://modelchoice.dev/models/claude-opus-4-6) | Anthropic | 53 | Observed 2026-11-21 · source benchlm:models |
| 21 | [dots3-note Preview](https://modelchoice.dev/models/dots3-note-preview) | Dots Studio | 52.6 | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 52.2 | Observed 2026-11-21 · source benchlm:models |
| 23 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 52.1 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Qwen4 Max](https://modelchoice.dev/models/qwen4-max) | Alibaba | 51.7 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Muse Spark](https://modelchoice.dev/models/muse-spark) | Meta | 50.4 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Claude Sonnet 4.6](https://modelchoice.dev/models/claude-sonnet-4-6) | Anthropic | 49 | Observed 2026-11-21 · source benchlm:models |
| 27 | [MiMo-V2.5-Pro](https://modelchoice.dev/models/mimo-v2-5-pro) | Xiaomi | 48 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Inkling-Small](https://modelchoice.dev/models/inkling-small) | Thinking Machines Lab | 47.8 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Agents-A1](https://modelchoice.dev/models/agents-a1) | InternScience | 47.6 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Step 5 Preview](https://modelchoice.dev/models/step-5-preview) | StepFun | 46.5 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Inkling](https://modelchoice.dev/models/inkling) | Thinking Machines Lab | 46 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Ornith-1.5-397B](https://modelchoice.dev/models/ornith-1-5-397b) | Ornith AI | 44.6 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Qwen3.8 Max](https://modelchoice.dev/models/qwen3-8-max) | Alibaba | 43.6 | Observed 2026-11-21 · source benchlm:models |
| 34 | [DeepSeek V4 Pro](https://modelchoice.dev/models/deepseek-v4-pro) | DeepSeek | 42.7 | Observed 2026-11-21 · source benchlm:models |
| 34 | [DeepSeek V4 Pro 0813](https://modelchoice.dev/models/deepseek-v4-pro-max) | DeepSeek | 42.7 | Last good 2026-11-18 · source benchlm:models |
| 36 | [DeepSeek V4.1 Flash 1017](https://modelchoice.dev/models/deepseek-v4-1-flash) | DeepSeek | 42.6 | Observed 2026-11-21 · source benchlm:models |
| 37 | [GPT-5.4 mini](https://modelchoice.dev/models/gpt-5-4-mini) | OpenAI | 41.5 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 41.4 | Observed 2026-11-21 · source benchlm:models |
| 39 | [GLM-5.2](https://modelchoice.dev/models/glm-5-2) | Z.AI | 40.5 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 40.2 | Observed 2026-11-21 · source benchlm:models |
| 41 | [GPT-5.4 nano](https://modelchoice.dev/models/gpt-5-4-nano) | OpenAI | 37.7 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Ling 3.1 Flash](https://modelchoice.dev/models/ling-3-1-flash) | InclusionAI | 37.44 | Observed 2026-11-21 · source benchlm:models |
| 43 | [Qwen3.8-Omni-Flash](https://modelchoice.dev/models/qwen3-8-omni-flash) | Alibaba | 36.5 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Qwen3.8-Flash-Next](https://modelchoice.dev/models/qwen3-8-flash-next) | Alibaba | 35.9 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Grok 4.3](https://modelchoice.dev/models/grok-4-3) | xAI | 35 | Observed 2026-11-21 · source benchlm:models |
| 46 | [DeepSeek V4 Flash 0731](https://modelchoice.dev/models/deepseek-v4-flash-max) | DeepSeek | 34.8 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 34.7 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 34.7 | Observed 2026-11-21 · source benchlm:models |
| 49 | [GLM-5.1](https://modelchoice.dev/models/glm-5-1) | Z.AI | 31 | Observed 2026-11-21 · source benchlm:models |
| 50 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 30.8 | Observed 2026-11-21 · source benchlm:models |
| 50 | [Qwen3.8-27B](https://modelchoice.dev/models/qwen3-8-27b) | Alibaba | 30.8 | Observed 2026-11-21 · source benchlm:models |
| 52 | [GLM-5](https://modelchoice.dev/models/glm-5) | Z.AI | 30.5 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 30.1 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Nemotron 3.5 Super VL 120B A12B](https://modelchoice.dev/models/nemotron-3-5-super-vl-120b-a12b) | NVIDIA | 29.2 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Nemotron 3.5 Super VL 120B A12B NVFP4](https://modelchoice.dev/models/nemotron-3-5-super-vl-120b-a12b-nvfp4) | NVIDIA | 29 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 28.8 | Observed 2026-11-21 · source benchlm:models |
| 57 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 28.7 | Observed 2026-11-21 · source benchlm:models |
| 58 | [MiniMax M2.7](https://modelchoice.dev/models/minimax-m2-7) | MiniMax | 28 | Observed 2026-11-21 · source benchlm:models |
| 59 | [A.X K2](https://modelchoice.dev/models/a-x-k2) | SK Telecom | 27.8 | Observed 2026-11-21 · source benchlm:models |
| 60 | [Nemotron 3 Ultra](https://modelchoice.dev/models/nemotron-3-ultra-500b) | NVIDIA | 26.7 | Observed 2026-11-21 · source benchlm:models |
| 61 | [Gemma 4 31B](https://modelchoice.dev/models/gemma-4-31b) | Google | 26.5 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Ornith-1.5-35B-A3B](https://modelchoice.dev/models/ornith-1-5-35b-a3b) | Ornith AI | 25.6 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Hy3 Preview](https://modelchoice.dev/models/hy3-preview) | Tencent | 25.5 | Observed 2026-11-21 · source benchlm:models |
| 64 | [GLM-4.7](https://modelchoice.dev/models/glm-4-7) | Z.AI | 24.8 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 24 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Ling 3.0 Flash](https://modelchoice.dev/models/ling-3-0-flash) | InclusionAI | 22.7 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 21.4 | Observed 2026-11-21 · source benchlm:models |
| 68 | [Ornith-1.5-9B](https://modelchoice.dev/models/ornith-1-5-9b) | Ornith AI | 20.2 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Gemini 2.5 Pro](https://modelchoice.dev/models/gemini-2-5-pro) | Google | 18.8 | Observed 2026-11-21 · source benchlm:models |
| 70 | [K-EXAONE 2.0](https://modelchoice.dev/models/k-exaone-2-0) | LG AI Research | 18.3 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Nemotron 3 Super 100B](https://modelchoice.dev/models/nemotron-3-super-100b) | NVIDIA | 18.26 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Qwen3 235B 2507 (Reasoning)](https://modelchoice.dev/models/qwen3-235b-2507-reasoning) | Alibaba | 18.2 | Last good 2026-11-18 · source benchlm:models |
| 73 | [DeepSeek-R1-0528](https://modelchoice.dev/models/deepseek-r1-0528) | DeepSeek | 17.7 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Gemma 4 26B A4B](https://modelchoice.dev/models/gemma-4-26b-a4b) | Google | 17.2 | Observed 2026-11-21 · source benchlm:models |
| 75 | [DeepSeek V3.1 (Reasoning)](https://modelchoice.dev/models/deepseek-v3-1-reasoning) | DeepSeek | 15.9 | Last good 2026-11-18 · source benchlm:models |
| 76 | [GPT-OSS 120B](https://modelchoice.dev/models/gpt-oss-120b) | OpenAI | 14.9 | Observed 2026-11-21 · source benchlm:models |
| 77 | [GPT-OSS 20B](https://modelchoice.dev/models/gpt-oss-20b) | OpenAI | 10.9 | Observed 2026-11-21 · source benchlm:models |
| 78 | [Nemotron 3 Nano 30B](https://modelchoice.dev/models/nemotron-3-nano-30b) | NVIDIA | 10.6 | Observed 2026-11-21 · source benchlm:models |
| 79 | [MiniCPM5-2B](https://modelchoice.dev/models/minicpm5-2b) | OpenBMB | 8.9 | Observed 2026-11-21 · source benchlm:models |
| 80 | [LFM2.5-24B-A2B](https://modelchoice.dev/models/lfm2-5-24b-a2b) | LiquidAI | 7.4 | Observed 2026-11-21 · source benchlm:models |
| 81 | [LFM3-1.7B](https://modelchoice.dev/models/lfm3-1-7b) | LiquidAI | 7.17 | Observed 2026-11-21 · source benchlm:models |
| 82 | [Kimi K2](https://modelchoice.dev/models/kimi-k2) | Moonshot AI | 4.7 | 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.
