Skip to main content
Evaluation sources/Humanity’s Last Exam
ParticipatingReasoning

Humanity’s Last Exam

Artificial Analysis · Public model evaluation results from Humanity’s Last Exam.

Official evaluation
Source description

This source measures concrete delivery performance in Reasoning; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Claude Fable 5.20.7428174295.12026-11-10
Claude Opus 5.50.6135310583.42026-11-05
Claude Fable 5.10.5912882381.42026-11-05
Gemini 4 Argon0.5708989879.62026-11-05
Claude Fable 50.5546802678.12026-11-05
Claude Sonnet 5.50.5495829577.72026-11-05
Claude Opus 50.5486561677.62026-11-05
GPT-6 Astra0.5468025977.42026-11-05
Muse Wonder Full0.5361445876.52026-11-05
Muse Wonder Full0.5361445876.52026-10-17
Muse Wonder Full0.5361445876.52026-10-18
GPT-6.1 Sol0.529193775.82026-11-05
Muse Wonder0.5009267873.32026-10-17
Muse Wonder0.5009267873.32026-11-05
Muse Wonder0.5009267873.32026-10-18
GPT-5.6 Sol0.4949026972.72026-11-05
MiMo V2.6 Pro0.4935125172.62026-11-05
Muse Spark 1.30.4870250272.02026-11-05
Claude Opus 4.80.4865616372.02026-11-05
MiniMax M3.1 Flash0.4796107571.42026-11-05
GPT-6 Sol0.4791473671.32026-11-05
Gemini 3.8 Flash0.4782205771.22026-11-05
Gemini 3.1 Pro Preview0.4703429170.52026-11-05
Kimi K30.4689527370.42026-11-05
Step 5 Preview0.4647822170.02026-11-05
GPT-6.1 Terra0.4624652569.82026-11-05
Muse Spark 1.10.4620018569.82026-11-05
GPT-5.50.4578313369.42026-11-05
Muse Spark 1.20.4545875869.12026-11-05
Claude Haiku 5.50.4439295668.12026-11-05
Grok 4.60.4406858267.82026-11-05
GPT-5.40.4374420867.52026-11-05
Ling-3.1-flash-10190.4346617267.32026-11-05
DeepSeek V4.1 Flash 10170.4332715567.22026-11-05
Grok 4.70.4314179867.02026-11-05
Qwen3.8 Max0.430491266.92026-11-05
GPT-5.6 Terra0.4291010266.82026-11-05
Grok 4.50.4267840666.62026-11-05
Claude Opus 4.70.4230769266.32026-11-05
GLM 5.30.4226135366.22026-11-05
Claude Sonnet 50.412882365.32026-11-05
GLM-5.20.4114921265.22026-11-05
DeepSeek V4 Pro 08130.4101019565.12026-11-05
Gemini 3.6 Flash0.4082483864.92026-11-05
Qwen3.7 Max0.4050046364.62026-11-05
Claude Opus 4.60.3994439364.12026-11-05
GLM-5.3 Flash0.3985171564.02026-11-05
GLM-5.3 Flash0.3985171564.02026-10-18
GLM-5.3 Flash0.3985171564.02026-10-17
Gemini 3 Pro Preview0.3971269763.92026-11-05
GPT-5.6 Luna0.3948100163.72026-11-05
Ling-3.1-flash0.3943466263.72026-10-17
Ling-3.1-flash0.3943466263.72026-11-05
Ling-3.1-flash0.3943466263.72026-10-18
DeepSeek V4.1 Flash0.3924930563.52026-11-05
MiniMax-M30.389712763.22026-11-05
DeepSeek V4 Flash 07310.3855421762.92026-11-05
GPT-6 Luna0.3850787862.82026-11-05
GPT-5.20.3767377262.12026-11-05
DeepSeek V4 Pro0.3753475461.92026-11-05
Kimi K2.60.3748841561.92026-11-05
Grok 4.30.372103861.72026-11-05
Gemini 3 Flash Preview0.3656163161.12026-11-05
MiMo-V2.5-Pro0.3568118660.32026-11-05
Qwen3.7 Plus0.3563484760.22026-11-05
MiMo V2.6 Flash0.3507877759.72026-10-17
MiMo V2.6 Flash0.3507877759.72026-10-18
MiMo V2.6 Flash0.3507877759.72026-11-05
Kimi K2.7 Code0.3503243759.72026-11-05
Mistral Large 40.3503243759.72026-10-28
Grok 4.200.3452270659.22026-10-11
Nex-N2-Pro0.337349458.52026-11-05
LongCat-2.00.3368860158.52026-11-05
Claude Sonnet 4.60.3359592258.42026-11-05
Hy30.3345690558.32026-11-05
Inkling Small0.3331788758.12026-11-05
Grok 4.20 (Reasoning)0.3239110357.32026-11-05
Inkling0.3188137256.82026-11-05
Qwen3.6 Max Preview0.308155755.92026-11-05
Kimi K2.50.3072289255.82026-11-05
MiMo-V2-Pro0.3044485655.62026-11-05
Claude Opus 4.50.3012048255.32026-11-05
GLM-5.10.3007414355.22026-11-05
MiniMax-M2.70.2961075154.82026-11-05
GLM-50.2928637654.52026-11-05
Qwen3.5 397B-A17B0.2896200254.22026-11-05
GPT-50.284986153.82026-11-05
Nemotron 3 Ultra 550B A55B0.2840593153.72026-11-05
GPT-5.4 mini0.2812789653.52026-11-05
Qwen3 Max Thinking0.2798887953.32026-11-05
Qwen3.6 Plus0.2784986153.22026-11-05
Hy3 preview0.2775718353.12026-11-05
GLM-5-Turbo0.2775718353.12026-11-05
GLM-4.70.2738646952.82026-11-05
MiMo-V2.50.2720111252.62026-11-05
Qwen3.5 122B-A10B0.2520852650.82026-11-05
DeepSeek V3.20.2455977850.22026-11-05
Grok 4.20 (Non-Reasoning)0.2451343850.22026-11-05
Step 3.5 Flash 26030.2446709950.22026-11-05
Qwen3.5 27B0.2391102949.72026-11-05
Ling-3.0-flash (free)0.2367933349.52026-11-05
MiniMax-M2.10.2316960149.02026-11-05
Qwen3.6 27B0.2307692348.92026-11-05
MiMo-V2-Flash0.2284522748.72026-11-05
Gemini 2.5 Pro0.2252085348.42026-11-05
Qwen3.6 35B-A3B0.2224281748.22026-11-05
MiMo-V2-Omni0.22103848.02026-11-05
Ring-2.6-1T0.2159406947.62026-11-05
GPT-5 mini0.2145505147.42026-11-05
Step 3.7 Flash0.2140871247.42026-11-05
Step 3.5 Flash0.2113067747.22026-11-05
Qwen3.5 35B-A3B0.2103799847.12026-11-05
Nemotron 3 Super 120B A12B0.2075996346.82026-11-05
MiniMax-M2.50.2052826746.62026-11-05
o30.200546.22026-11-05
gpt-oss-120b0.1960148345.82026-11-05
Gemini 3.5 Flash Lite0.1881371645.12026-11-05
Claude Sonnet 4.50.1779425444.12026-11-05
Gemini 3.1 Flash Lite0.1719184443.62026-11-05
GLM-5V-Turbo0.1714550543.62026-11-05
Mercury 20.1714550543.62026-11-05
o4-mini0.1654309543.02026-10-11
o4 Mini High0.1654309543.02026-11-05
DeepSeek V3.1 Terminus0.1635773942.82026-11-05
KAT-Coder-Pro V20.1612604342.62026-11-05
Trinity Large Thinking0.1584800742.42026-11-05
Gemma 4 12B Base0.1566265142.22026-11-05
Qwen3.5 9B0.1492122341.62026-11-05
DeepSeek V3.2 Exp0.1487488441.52026-11-05
GLM-4.60.1445783141.12026-11-05
DeepSeek V3.10.1427247541.02026-11-05
Mistral Medium 3.50.1376274340.52026-11-05
MiniMax-M20.1367006540.42026-11-05
GLM-4.50.1297497739.82026-11-05
Gemini 2.5 Flash0.1214087139.02026-11-05
o3 Mini High0.120439.02026-11-05
Nemotron Cascade 2 30B A3B0.1200185438.92026-11-05
Command A Plus0.1195551438.92026-11-05
Qwen3 Max0.1190917538.82026-11-05
Nemotron 3 Nano 30B A3B0.1139944438.42026-11-05
Qwen3 235B A22B Instruct 25070.1112140938.12026-11-05
North Mini Code0.110750738.12026-11-05
Sarvam 105B0.110287338.02026-11-05
gpt-oss-20b0.1098239138.02026-11-05
Qwen3 235B-A22B0.109838.02026-11-05
Claude Haiku 4.50.1037998137.52026-11-05
Solar Pro 30.1028730337.42026-11-05
Qwen3 Coder Next0.1014828537.22026-11-05
GLM-4.6V0.0963855436.82026-11-05
GPT-5 nano0.0949953736.72026-11-05
Ling-2.6-1T0.087117736.02026-11-05
DeepSeek-R10.08535.82026-11-05
o3-mini0.079135.22026-11-05
Qwen3-Next 80B-A3B Instruct0.0764596835.02026-11-05
GLM-4.7-Flash0.0759962934.92026-11-05
Sarvam 30B0.0750695134.92026-11-05
Qwen3 32B0.074134.82026-11-05
GLM-4.5-Air0.0704355934.42026-11-05
o10.070134.42026-11-03
Qwen3 30B A3B Instruct 25070.0690454134.32026-11-05
Gemini 2.5 Flash-Lite0.0681186334.22026-11-05
Qwen3 VL 32B Instruct0.0681186334.22026-11-05
Qwen3 VL 235B A22B Instruct0.0662650634.12026-11-05
Sonar Pro0.065534.02026-11-05
Olmo 3 32B Think0.0644114933.92026-11-05
Kimi K2 09050.063948133.92026-11-05
GLM-4.5V0.0630213233.82026-11-05
Qwen3 VL 30B A3B Instruct0.0630213233.82026-11-05
Ling-2.6-flash0.0625579233.72026-11-05
Qwen3 30B A3B0.061633.72026-11-05
Llama 3.3 Nemotron Super 49B v10.056233.22026-11-05
Nemotron Nano 12B v2 VL0.0551436533.12026-11-05
Ministral 3 3B0.0537534832.92026-11-05
R1 Distill Llama 70B0.051332.72026-11-05
Granite 4.0 Micro0.0500463432.62026-11-05
Llama 4 Maverick0.0491195632.52026-11-05
Sonar0.048832.52026-11-05
Nemotron Nano 9B v20.0486561632.52026-11-05
Nemotron 3 Nano Omni 30B A3B Reasoning0.0481927732.42026-11-05
DeepSeek V3 03240.047432.42026-11-05
Ministral 3 14B0.046339232.32026-11-05
Qwen3-Coder 480B-A35B Instruct0.0454124232.22026-11-05
Qwen3 14B0.045332.22026-11-05
Reka Flash 30.044432.12026-11-05
Ministral 3 8B0.0426320731.92026-11-05
Gemini 2.0 Flash0.042631.92026-11-05
Mistral Large 30.0417052831.92026-11-05
Qwen Turbo0.040931.82026-11-05
Mistral Medium 3.50.040531.72026-11-05
Command A0.0403151131.72026-11-05
Hermes 3 70B Instruct0.039931.72026-11-05
Qwen3 8B0.038931.62026-11-05
Qwen3-Coder 30B-A3B Instruct0.0384615431.62026-11-05
Granite 4.1 8B0.0379981531.52026-11-05
Llama 4 Scout0.037831.52026-11-05
Mistral Small 30.037631.52026-11-05
Phi 40.037631.52026-11-05
Qwen2.5 72B Instruct0.035631.32026-11-05
Qwen2.5 Coder 32B Instruct0.035131.32026-11-05
Mistral Large0.03531.32026-11-05
Qwen3 VL 8B Instruct0.0268767430.52026-11-05

Frequently asked questions