CtrlAltDebrief

Humanity's Last Exam benchmark

388 AI models ranked on Humanity's Last Exam. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.

Top model today

Claude Fable 5 (Anthropic) leads at 53%, from $10.00 per 1M input.

Data via arXiv:2501.14249 →

Models ranked

388

on this benchmark

Top score

53%

current leader

Type

Single eval

benchmark

Updated

15 July 2026

last source fetch

Cost vs Humanity's Last Exam

206 priced models
Most attractive quadrant (cheap + high)
= reasoning model (extended thinking)
0%20%40%60%$0.01$0.03$0.1$0.3$1$3$10COST / 1M INPUT TOKENS (log) →HUMANITY'S LAST EXAM SCORE ↑Claude Fable 5GPT-5.6 SolClaude Opus 4.8Muse Spark 1.1Gemini 3.1 Pro PreviewGPT-5.5GPT-5.6 TerraGPT-5.4GPT-5.6 LunaMiniMax M3MiniMax M2.7GPT-5.4 NanoGemma 4 31BMimo V2 Flashgpt-oss-120bgpt-oss-20bLlama 3.2 3B InstructQwen2 5 Coder 7B Instruct

Each labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.

Models ranked on Humanity's Last Exam

highest score first · 388 models
Maker
#
1Claude Fable 5Anthropic53%$10.00$50.00
2GPT-5.6 SolOpenAI47%$5.00$30.00
3Claude Opus 4.8Anthropic46%$5.00$25.00
4Muse Spark 1.1Other45%$1.25$4.25
5Gemini 3.1 Pro PreviewGoogle45%$2.00$12.00
6GPT-5.5OpenAI44%$5.00$30.00
7GPT-5.6 TerraOpenAI42%$2.50$15.00
8GPT-5.4OpenAI42%$2.50$15.00
9Gemini 3.5 FlashGoogle41%$1.50$9.00
10Grok 4.5xAI40%$2.00$6.00
11GLM 5.2Zhipu40%$1.40$4.40
12Muse SparkMeta40%n/an/a
13GPT-5.3 CodexOpenAI40%n/an/a
14Claude Opus 4.7Anthropic40%$5.00$25.00
15Claude Sonnet 5Anthropic40%$2.00$10.00
16Qwen3.7 MaxAlibaba38%n/an/a
17GPT-5.6 LunaOpenAI37%$1.00$6.00
18Gemini 3 ProGoogle37%$2.00$12.00
19MiniMax M3MiniMax37%$0.30$1.20
20Claude Opus 4.6Anthropic37%reasoning: adaptive$5.00$25.00
21Grok Build 0.1 0616Spacexai36%n/an/a
22Kimi K2.6Moonshot36%n/an/a
23DeepSeek V4 ProDeepSeek36%$0.43$0.87
24GPT-5.2OpenAI35%$1.75$14.00
25Grok 4.3xAI35%$1.25$2.50
26Gemini 3 FlashGoogle35%reasoning: truen/an/a
27MiMo-V2.5-ProXiaomi34%$1.00$3.00
28GPT-5.2-CodexOpenAI33%$1.75$14.00
29Qwen3.7 PlusAlibaba33%n/an/a
30Kimi K2.7 CodeMoonshot33%$0.95$4.00
31Nex-N2-ProNex-agi32%n/an/a
32Grok 4.20 0309 v2Spacexai32%n/an/a
33DeepSeek V4 FlashDeepSeek32%n/an/a
34LongCat 2.0Longcat32%n/an/a
35Hy3-previewTencent32%n/an/a
36Grok 4.20 0309Spacexai30%n/an/a
37Claude Sonnet 4.6Anthropic30%reasoning: adaptive$3.00$15.00
38Kimi K2.5Moonshot29%$0.50$2.80
39Qwen3.6 Max PreviewAlibaba29%n/an/a
40Claude Opus 4.5Anthropic28%reasoning: true$5.00$25.00
41MiMo-V2-ProXiaomi28%n/an/a
42MiniMax M2.7MiniMax28%$0.26$0.55
43GLM 5.1Zhipu28%$1.05$3.50
44Qwen3.5 397B A17BAlibaba27%$0.60$3.60
45GLM 5Zhipu27%$0.80$2.56
46GPT-5.4 MiniOpenAI27%$0.75$4.50
47Nemotron 3 UltraNVIDIA27%n/an/a
48GPT-5OpenAI27%$1.25$10.00
49GPT-5.1OpenAI26%$1.25$10.00
50GPT-5.4 NanoOpenAI26%$0.20$1.25
1–50 of 388
Page 1 of 8
Prices are on-demand list rates. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage.

Frequently asked questions

What is the Humanity's Last Exam benchmark?

A frontier academic benchmark of 2,500 expert-written questions spanning mathematics, the humanities and the natural sciences, in multiple-choice and short-answer formats. Each question has an unambiguous, verifiable answer that cannot be found by quick internet retrieval, and models are scored on accuracy.

Which AI model scores highest on Humanity's Last Exam?

Claude Fable 5 (Anthropic) leads with 53%, from $10.00 per 1M input tokens.

How many models are ranked on Humanity's Last Exam?

388 models carry a Humanity's Last Exam score. Scores come from Artificial Analysis; where a model has a live API price it is verified against LiteLLM and OpenRouter, and models with no current price are listed without one.

Other benchmarks

compare the same models on a different eval
Intelligence Indexcomposite indexCoding Indexcomposite indexAgentic Indexcomposite indexGPQA DiamondleaderboardMMLU-ProleaderboardMMMU-ProleaderboardLiveCodeBenchleaderboardSciCodeleaderboardTerminalBench HardleaderboardTerminalBench v2.1leaderboardτ²-benchleaderboardτ-bench BankingleaderboardAPEX AgentsleaderboardIT-Bench SREleaderboardGDPvalleaderboardCritPtleaderboardOmniscienceleaderboardIFBenchleaderboardLong-Context Reasoningcomposite indexSWE-bench VerifiedleaderboardSWE-bench ProleaderboardAIME 2026leaderboardARC-AGI-2leaderboardAA-Briefcaseleaderboard
Benchmark scores via Artificial Analysis · pricing verified against LiteLLM + OpenRouter · refreshed daily · updated 15 July 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI