GDPval benchmark

115 AI models ranked on GDPval. 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 1759.6, from $10.00 per 1M input.

Data via arXiv:2510.04374

Models ranked

115

on this benchmark

Top score

1759.6

current leader

Type

Single eval

benchmark

Updated

15 July 2026

last source fetch

Cost vs GDPval

74 priced models
Most attractive quadrant (cheap + high)
= reasoning model (extended thinking)

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 GDPval

highest score first · 115 models
Maker
#
1Claude Fable 5Anthropic1759.6$10.00$50.00
2GPT-5.6 SolOpenAI1747.8$5.00$30.00
3Claude Sonnet 5Anthropic1606.7$2.00$10.00
4Claude Opus 4.8Anthropic1600.1$5.00$25.00
5GPT-5.6 TerraOpenAI1593.0$2.50$15.00
6GPT-5.6 LunaOpenAI1591.8$1.00$6.00
7Grok 4.5xAI1538.5$2.00$6.00
8GLM 5.2Zhipu1513.9$1.40$4.40
9Claude Opus 4.7Anthropic1499.9$5.00$25.00
10GPT-5.5OpenAI1493.7$5.00$30.00
11MiniMax M3MiniMax1394.8$0.30$1.20
12GPT-5.4OpenAI1394.7$2.50$15.00
13Claude Sonnet 4.6Anthropic1378reasoning: adaptive$3.00$15.00
14Muse Spark 1.1Other1374.3$1.25$4.25
15Gemini 3.5 FlashGoogle1348.8$1.50$9.00
16DeepSeek V4 ProDeepSeek1306.1$0.43$0.87
17Qwen3.7 MaxAlibaba1273.2n/an/a
18MiMo-V2.5-ProXiaomi1265.4$1.00$3.00
19JT-4.1 Flash 236B A21BChina-mobile1264.5n/an/a
20Nex-N2-ProNex-agi1256.9n/an/a
21GLM 5.1Zhipu1256.7$1.05$3.50
22Hy3-previewTencent1213.9n/an/a
23Grok Build 0.1 0616Spacexai1211.4n/an/a
24Kimi K2.6Moonshot1190.4n/an/a
25DeepSeek V4 FlashDeepSeek1188.5n/an/a
26Kimi K2.7 CodeMoonshot1186.8$0.95$4.00
27GPT-5.4 MiniOpenAI1170.8$0.75$4.50
28GLM 4.7Zhipu1165.3$0.40$1.50
29Nemotron 3 UltraNVIDIA1163.8n/an/a
30MiniMax M2.7MiniMax1157.9$0.26$0.55
31MiMo-V2.5Xiaomi1145.0n/an/a
32Muse SparkMeta1143.7n/an/a
33Qwen3.6 27BAlibaba1139.7$0.15$0.50
34Qwen3.6 PlusAlibaba1135.4$0.33$1.95
35GPT-5.4 NanoOpenAI1099.9$0.20$1.25
36Grok 4.3xAI1096.0reasoning: false$1.25$2.50
37GPT-5OpenAI1074.8$1.25$10.00
38Claude 4.5 SonnetAnthropic1052.5reasoning: true$3.00$15.00
39Qwen3.6 35B A3BAlibaba1048.7$0.14$0.45
40LongCat 2.0Longcat1021.8n/an/a
41Step 3.7 FlashStepfun1017.0n/an/a
42Kimi K2.5Moonshot1008.5$0.50$2.80
43GPT-5.1OpenAI987.5$1.25$10.00
44Qwen3.5-122B-A10BAlibaba978.0$0.25$1.75
45Gemini 3.1 Pro PreviewGoogle962.3$2.00$12.00
46Qwen3.5 397B A17BAlibaba961.9$0.60$3.60
47GPT-5 MiniOpenAI936.7$0.25$2.00
48Qwen3.7 PlusAlibaba936.3n/an/a
49GLM 4.6Zhipu933.6reasoning: true$0.40$1.75
50Mistral Medium 3.5Mistral930.9$1.50$7.50
150 of 115
Page 1 of 3
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 GDPval benchmark?

GDPval (OpenAI, 2025) evaluates AI on 1,320 real-world knowledge-work tasks drawn from 44 occupations across the nine largest US GDP sectors, built from the work of experienced professionals. Expert graders blind-compare model deliverables against professional work, producing win or tie rates.

Which AI model scores highest on GDPval?

Claude Fable 5 (Anthropic) leads with 1759.6, from $10.00 per 1M input tokens.

How many models are ranked on GDPval?

115 models carry a GDPval 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
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