Humanity's Last Exam
HLE - Humanity's Last Exam - extremely difficult expert-level questions across domains.
Category
STEM & Reasoning
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for Humanity's Last Exam
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.6-35B-A3B |
36.55%
|
16.04.2026 | Verified |
| Gemma4-31B-it |
32.95%
|
16.04.2026 | Unverified |
| Qwen3.5-35B-A3B |
38.45%
|
16.04.2026 | Unverified |
| Gemma4-26B-A4B |
12.50%
|
16.04.2026 | Unverified |
| Qwen3.6-27B |
41.48%
|
22.04.2026 | Verified |
| Qwen3.5-397B-A17B |
50.38%
|
22.04.2026 | Unverified |
| Claude 4.5 Opus |
54.36%
|
22.04.2026 | Unverified |
| Qwen3.5-27B |
42.05%
|
16.04.2026 | Unverified |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
46.59%
|
04.06.2026 | Verified |
| MiniMax-M2.7 |
39.77%
|
04.06.2026 | Unverified |
| GLM-5.1 |
47.54%
|
04.06.2026 | Unverified |
| Kimi K2.6 |
61.93%
|
04.06.2026 | Unverified |
| DeepSeek-V4-Pro |
67.42%
|
04.06.2026 | Unverified |
| Qwen3.8-27B |
54.36%
|
18.08.2026 | Verified |
| Qwen3.7-Plus |
61.74%
|
18.08.2026 | Unverified |
| Muse Glimmer-30B |
37.69%
|
18.08.2026 | Unverified |
| Opus4.6 Max |
71.78%
|
18.08.2026 | Unverified |
| Fable-5 |
96.97%
|
18.08.2026 | Unverified |
| GPT-5.6 Sol |
85.42%
|
18.08.2026 | Unverified |
| Claude Opus 4.8 |
82.58%
|
18.08.2026 | Unverified |
| Qwen3.8-2.4T-A95B |
78.60%
|
18.08.2026 | Verified |
| Muse-Glimmer-30B |
37.69%
|
01.08.2026 | Verified |
| GLM-5.2 |
72.73%
|
17.06.2026 | Verified |
| Gemini 3.1 Pro |
81.25%
|
17.06.2026 | Unverified |
| GPT-5.5 |
74.43%
|
17.06.2026 | Unverified |
| MiniMax-M3 |
66.10%
|
17.06.2026 | Unverified |
| Qwen3.7-Max |
74.43%
|
17.06.2026 | Unverified |
| Qwen3.5-122B-A10B |
43.94%
|
01.02.2026 | Verified |
| Qwen3-235B-A22B |
30.49%
|
01.02.2026 | Unverified |
| GPT-5-mini 2025-08-07 |
32.77%
|
01.02.2026 | Unverified |
| Ornith-1.5-35B-A3B |
44.51%
|
19.08.2026 | Verified |
| Ornith-1.0-35B-A3B |
35.42%
|
19.08.2026 | Unverified |
| Gemma-4-31B |
32.95%
|
19.08.2026 | Unverified |
| GPT-5.4 |
71.40%
|
23.08.2026 | Verified |
| Claude Opus 4.6 |
71.78%
|
23.08.2026 | Verified |
| Kimi K2.5 |
53.03%
|
23.08.2026 | Verified |
| GPT-OSS-120B |
24.24%
|
08.08.2025 | Verified |
| GPT-OSS-20B |
16.67%
|
05.08.2025 | Verified |
| Opus-4.6 |
71.78%
|
26.06.2026 | Verified |
| DeepSeek-V4-Pro |
67.42%
|
26.06.2026 | Verified |
| DeepSeek-V4-Flash |
61.93%
|
26.06.2026 | Verified |
| DeepSeek-V4-Pro-0813 |
76.89%
|
13.08.2026 | Verified |
| DeepSeek-V4-Flash-0731 |
67.61%
|
13.08.2026 | Verified |
| Kimi K3 |
78.41%
|
13.08.2026 | Verified |
| Opus-4.8 |
90.34%
|
13.08.2026 | Verified |
| MiniCPM5-2B |
12.88%
|
— | Verified |
| Hy3 |
61.17%
|
28.08.2026 | Verified |
| Hy4 preview |
78.22%
|
28.08.2026 | Verified |
| DeepSeek V4 Pro |
76.89%
|
28.08.2026 | Verified |
| GLM-5.3 |
76.14%
|
28.08.2026 | Verified |
| Claude Opus 5 |
100.00%
|
28.08.2026 | Verified |
| Spark-X2.5-4B |
19.32%
|
— | Verified |
| Spark-X2.5-1.7B |
7.95%
|
— | Verified |
| Qwen3.5-9B |
23.11%
|
— | Verified |
| Qwen3.5-4B |
12.31%
|
— | Verified |
| Qwen3.5-2B |
2.10
|
— | Verified |
| Gemma4-E4B |
3.41%
|
— | Verified |
| Gemma4-E2B |
0.76%
|
— | Verified |
| LFM2.5-2.6B |
7.77%
|
— | Verified |
| granite-4.2-3B |
8.52%
|
— | Verified |
| Nemotron-3-Nano-4B |
5.30%
|
— | Verified |
| LFM2.5-8B-A1B |
9.09%
|
— | Verified |
| DeepSeek-V4.1-Flash |
65.72%
|
10.09.2026 | Verified |
| Gemma4-12B |
20.83%
|
02.07.2026 | Verified |