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 Opus 5.50.6135310584.42026-11-05
Claude Fable 5.10.5912882382.42026-11-05
Gemini 4 Argon0.5708989880.52026-11-05
Claude Fable 50.5546802679.02026-11-05
Claude Sonnet 5.50.5495829578.52026-11-05
Claude Opus 50.5486561678.42026-11-05
GPT-6 Astra0.5468025978.32026-11-05
Muse Wonder Full0.5361445877.32026-11-05
Muse Wonder Full0.5361445877.32026-10-17
Muse Wonder Full0.5361445877.32026-10-18
GPT-6.1 Sol0.529193776.62026-11-05
Muse Wonder0.5009267874.02026-10-17
Muse Wonder0.5009267874.02026-11-05
Muse Wonder0.5009267874.02026-10-18
GPT-5.6 Sol0.4949026973.52026-11-05
MiMo V2.6 Pro0.4935125173.42026-11-05
Muse Spark 1.30.4870250272.82026-11-05
Claude Opus 4.80.4865616372.72026-11-05
MiniMax M3.1 Flash0.4796107572.12026-11-05
GPT-6 Sol0.4791473672.02026-11-05
Gemini 3.8 Flash0.4782205771.92026-11-05
Gemini 3.1 Pro Preview0.4703429171.22026-11-05
Kimi K30.4689527371.12026-11-05
Step 5 Preview0.4647822170.72026-11-05
GPT-6.1 Terra0.4624652570.52026-11-05
Muse Spark 1.10.4620018570.52026-11-05
GPT-5.50.4578313370.12026-11-05
Muse Spark 1.20.4545875869.82026-11-05
Claude Haiku 5.50.4439295668.82026-11-05
Grok 4.60.4406858268.52026-11-05
GPT-5.40.4374420868.22026-11-05
Ling-3.1-flash-10190.4346617267.92026-11-05
DeepSeek V4.1 Flash 10170.4332715567.82026-11-05
Grok 4.70.4314179867.62026-11-05
Qwen3.8 Max0.430491267.52026-11-05
GPT-5.6 Terra0.4291010267.42026-11-05
Grok 4.50.4267840667.22026-11-05
Claude Opus 4.70.4230769266.92026-11-05
GLM 5.30.4226135366.82026-11-05
Claude Sonnet 50.412882365.92026-11-05
GLM-5.20.4114921265.82026-11-05
DeepSeek V4 Pro 08130.4101019565.72026-11-05
Gemini 3.6 Flash0.4082483865.52026-11-05
Qwen3.7 Max0.4050046365.22026-11-05
Claude Opus 4.60.3994439364.72026-11-05
GLM-5.3 Flash0.3985171564.62026-11-05
GLM-5.3 Flash0.3985171564.62026-10-18
GLM-5.3 Flash0.3985171564.62026-10-17
Gemini 3 Pro Preview0.3971269764.52026-11-05
GPT-5.6 Luna0.3948100164.32026-11-05
Ling-3.1-flash0.3943466264.22026-10-17
Ling-3.1-flash0.3943466264.22026-11-05
Ling-3.1-flash0.3943466264.22026-10-18
DeepSeek V4.1 Flash0.3924930564.02026-11-05
MiniMax-M30.389712763.82026-11-05
DeepSeek V4 Flash 07310.3855421763.42026-11-05
GPT-6 Luna0.3850787863.42026-11-05
GPT-5.20.3767377262.62026-11-05
DeepSeek V4 Pro0.3753475462.52026-11-05
Kimi K2.60.3748841562.42026-11-05
Grok 4.30.372103862.22026-11-05
Gemini 3 Flash Preview0.3656163161.62026-11-05
MiMo-V2.5-Pro0.3568118660.82026-11-05
Qwen3.7 Plus0.3563484760.72026-11-05
MiMo V2.6 Flash0.3507877760.22026-10-17
MiMo V2.6 Flash0.3507877760.22026-10-18
MiMo V2.6 Flash0.3507877760.22026-11-05
Kimi K2.7 Code0.3503243760.22026-11-05
Mistral Large 40.3503243760.22026-10-28
Grok 4.200.3452270659.72026-10-11
Nex-N2-Pro0.337349459.02026-11-05
LongCat-2.00.3368860158.92026-11-05
Claude Sonnet 4.60.3359592258.82026-11-05
Hy30.3345690558.72026-11-05
Inkling Small0.3331788758.62026-11-05
Grok 4.20 (Reasoning)0.3239110357.72026-11-05
Inkling0.3188137257.22026-11-05
Qwen3.6 Max Preview0.308155756.32026-11-05
Kimi K2.50.3072289256.22026-11-05
MiMo-V2-Pro0.3044485655.92026-11-05
Claude Opus 4.50.3012048255.62026-11-05
GLM-5.10.3007414355.62026-11-05
MiniMax-M2.70.2961075155.22026-11-05
GLM-50.2928637654.92026-11-05
Qwen3.5 397B-A17B0.2896200254.62026-11-05
GPT-50.284986154.12026-11-05
Nemotron 3 Ultra 550B A55B0.2840593154.02026-11-05
GPT-5.4 mini0.2812789653.82026-11-05
Qwen3 Max Thinking0.2798887953.72026-11-05
Qwen3.6 Plus0.2784986153.52026-11-05
GLM-5-Turbo0.2775718353.42026-11-05
Hy3 preview0.2775718353.42026-11-05
GLM-4.70.2738646953.12026-11-05
MiMo-V2.50.2720111252.92026-11-05
Qwen3.5 122B-A10B0.2520852651.12026-11-05
DeepSeek V3.20.2455977850.52026-11-05
Grok 4.20 (Non-Reasoning)0.2451343850.52026-11-05
Step 3.5 Flash 26030.2446709950.42026-11-05
Qwen3.5 27B0.2391102949.92026-11-05
Ling-3.0-flash (free)0.2367933349.72026-11-05
MiniMax-M2.10.2316960149.22026-11-05
Qwen3.6 27B0.2307692349.12026-11-05
MiMo-V2-Flash0.2284522748.92026-11-05
Gemini 2.5 Pro0.2252085348.62026-11-05
Qwen3.6 35B-A3B0.2224281748.42026-11-05
MiMo-V2-Omni0.22103848.22026-11-05
Ring-2.6-1T0.2159406947.82026-11-05
GPT-5 mini0.2145505147.62026-11-05
Step 3.7 Flash0.2140871247.62026-11-05
Step 3.5 Flash0.2113067747.32026-11-05
Qwen3.5 35B-A3B0.2103799847.22026-11-05
Nemotron 3 Super 120B A12B0.2075996347.02026-11-05
MiniMax-M2.50.2052826746.82026-11-05
o30.200546.32026-11-05
gpt-oss-120b0.1960148345.92026-11-05
Gemini 3.5 Flash Lite0.1881371645.22026-11-05
Claude Sonnet 4.50.1779425444.32026-11-05
Gemini 3.1 Flash Lite0.1719184443.72026-11-05
Mercury 20.1714550543.72026-11-05
GLM-5V-Turbo0.1714550543.72026-11-05
o4-mini0.1654309543.12026-10-11
o4 Mini High0.1654309543.12026-11-05
DeepSeek V3.1 Terminus0.1635773942.92026-11-05
KAT-Coder-Pro V20.1612604342.72026-11-05
Trinity Large Thinking0.1584800742.52026-11-05
Gemma 4 12B Base0.1566265142.32026-11-05
Qwen3.5 9B0.1492122341.62026-11-05
DeepSeek V3.2 Exp0.1487488441.62026-11-05
GLM-4.60.1445783141.22026-11-05
DeepSeek V3.10.1427247541.02026-11-05
Mistral Medium 3.50.1376274340.52026-11-05
MiniMax-M20.1367006540.52026-11-05
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 4.50.1037998137.42026-11-05
Solar Pro 30.1028730337.32026-11-05
Qwen3 Coder Next0.1014828537.22026-11-05
GLM-4.6V0.0963855436.72026-11-05
GPT-5 nano0.0949953736.62026-11-05
Ling-2.6-1T0.087117735.92026-11-05
DeepSeek-R10.08535.72026-11-05
o3-mini0.079135.12026-11-05
Qwen3-Next 80B-A3B Instruct0.0764596834.92026-11-05
GLM-4.7-Flash0.0759962934.92026-11-05
Sarvam 30B0.0750695134.82026-11-05
Qwen3 32B0.074134.72026-11-05
GLM-4.5-Air0.0704355934.32026-11-05
o10.070134.32026-11-03
Qwen3 30B A3B Instruct 25070.0690454134.22026-11-05
Gemini 2.5 Flash-Lite0.0681186334.12026-11-05
Qwen3 VL 32B Instruct0.0681186334.12026-11-05
Qwen3 VL 235B A22B Instruct0.0662650634.02026-11-05
Sonar Pro0.065533.92026-11-05
Olmo 3 32B Think0.0644114933.82026-11-05
Kimi K2 09050.063948133.72026-11-05
GLM-4.5V0.0630213233.72026-11-05
Qwen3 VL 30B A3B Instruct0.0630213233.72026-11-05
Ling-2.6-flash0.0625579233.62026-11-05
Qwen3 30B A3B0.061633.52026-11-05
Llama 3.3 Nemotron Super 49B v10.056233.02026-11-05
Nemotron Nano 12B v2 VL0.0551436532.92026-11-05
Ministral 3 3B0.0537534832.82026-11-05
R1 Distill Llama 70B0.051332.62026-11-05
Granite 4.0 Micro0.0500463432.52026-11-05
Llama 4 Maverick0.0491195632.42026-11-05
Sonar0.048832.42026-11-05
Nemotron Nano 9B v20.0486561632.32026-11-05
Nemotron 3 Nano Omni 30B A3B Reasoning0.0481927732.32026-11-05
DeepSeek V3 03240.047432.22026-11-05
Ministral 3 14B0.046339232.12026-11-05
Qwen3-Coder 480B-A35B Instruct0.0454124232.02026-11-05
Qwen3 14B0.045332.02026-11-05
Reka Flash 30.044431.92026-11-05
Ministral 3 8B0.0426320731.82026-11-05
Gemini 2.0 Flash0.042631.82026-11-05
Mistral Large 30.0417052831.72026-11-05
Qwen Turbo0.040931.62026-11-05
Mistral Medium 3.50.040531.62026-11-05
Command A0.0403151131.62026-11-05
Hermes 3 70B Instruct0.039931.52026-11-05
Qwen3 8B0.038931.42026-11-05
Qwen3-Coder 30B-A3B Instruct0.0384615431.42026-11-05
Granite 4.1 8B0.0379981531.42026-11-05
Llama 4 Scout0.037831.32026-11-05
Phi 40.037631.32026-11-05
Mistral Small 30.037631.32026-11-05
Qwen2.5 72B Instruct0.035631.12026-11-05
Qwen2.5 Coder 32B Instruct0.035131.12026-11-05
Mistral Large0.03531.12026-11-05
Qwen3 VL 8B Instruct0.0268767430.32026-11-05

Frequently asked questions