CtrlAltDebrief

GDPval benchmark

202 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.

Scores frozen

Claude Opus 5 (Anthropic) leads at 1844.7

Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Data via arXiv:2510.04374 →

Models ranked

202

on this benchmark

Top score

1844.7

on the frozen board

Type

Single eval

benchmark

Frozen

Aug 18, 2026

benchmark scores

Models ranked on GDPval

highest score first · 202 models
Maker
#
1Claude Opus 5Anthropic1844.7
$5.00
via Anthropic
$25.00
via Anthropic
2Grok 4.6xAI1747.5
$2.00
via xAI
$6.00
via xAI
3Claude Fable 5Anthropic1737.7
$10.00
via Anthropic
$50.00
via Anthropic
4GPT-5.6 SolOpenAI1723.0
$2.00
Routed quote
$10.00
Routed quote
5Qwen3.8 2.4T A95BAlibaba1720.4
$2.00
via Aihubmix
$6.00
via Aihubmix
6Kimi K3Moonshot1681.1
$0.70
Routed quote
$12.50
via Sail
7Muse Spark 1.2Other1628
$1.25
via Meta
$4.25
via Meta
8Claude Sonnet 5Anthropic1595.5
$2.00
via Anthropic
$10.00
via Anthropic
9Claude Opus 4.8Anthropic1583.7
$5.00
via Anthropic
$25.00
via Anthropic
10GPT-5.6 LunaOpenAI1578.3
$0.20
via OpenAI
$1.20
via OpenAI
11GPT-5.6 TerraOpenAI1576.3
$2.00
via OpenAI
$12.00
via OpenAI
12Qwen3.8 27BAlibaba1545.9
$0.04
Routed quote
$1.49
via Cerebras
13Gemini 3.7 FlashGoogle1531.5
$0.75
via Google
$3.75
via Google
14Grok 4.5xAI1524.4
$2.00
via xAI
$6.00
via xAI
15GLM 5.2Zhipu1505.2
$0.05
Routed quote
$1.98
via Scx AI
16GPT-5.5OpenAI1490.2
$5.00
via OpenAI
$30.00
via OpenAI
17Claude Opus 4.7Anthropic1489.5
$5.00
via Anthropic
$25.00
via Anthropic
18Gemini 3.6 FlashGoogle1422.2
$0.75
via Google
$3.75
via Google
19GPT-5.4OpenAI1394.0
$2.50
via Databricks
$15.00
via OpenAI
20MiniMax M3MiniMax1386.9
$0.23
via Wandb
$0.96
via Wandb
21Claude Sonnet 4.6Anthropic1374.3reasoning: adaptive
$3.00
via Databricks
$15.00
via Anthropic
22Muse Spark 1.1Other1374.2
$1.25
via Meta
$4.25
via Meta
23Gemini 3.5 FlashGoogle1343.4
$1.50
via Google
$9.00
via Google
24Solar Pro 4Other1275.8
$0.09
Routed quote
$0.36
Routed quote
25Motif 3Motif-technologies1274.5
n/a
n/a
26Qwen3.7 MaxAlibaba1271
$1.25
via Novita
$3.75
via Novita
27Inkling SmallThinking Machines1268.2
$0.45
via DeepInfra
$1.20
via Baseten
28MiMo-V2.5-ProXiaomi1265.8
$0.435
Routed quote
$0.87
Routed quote
29JT-4.1 Flash 236B A21BChina-mobile1263.4
n/a
n/a
30GLM 5.1Zhipu1257.8
$1.05
via DeepInfra
$3.50
via DeepInfra
31Motif 3 (Beta) (0714)Motif-technologies1256.7
n/a
n/a
32Nex-N2-ProOther1248.9
$0.25
Routed quote
$1.00
Routed quote
33InklingThinking Machines1238.7
$0.95
via DeepInfra
$4.05
via Baseten
34Grok Build 0.1 0616Spacexai1215.1
n/a
n/a
35Hy3Tencent1214.4
$0.132
Routed quote
$0.528
Routed quote
36G9v3-39A5BAi9stars1196.6
n/a
n/a
37Kimi K2.6Moonshot1190.4
$0.65
via Wandb
$3.40
via Novita
38Kimi K2.7 CodeMoonshot1189.9
$0.671
Routed quote
$3.35
Routed quote
39Agnes 2.5 Pro AlphaSapiens-ai1175.6
n/a
n/a
40GPT-5.4 MiniOpenAI1171.8
$0.75
via Databricks
$4.50
via OpenAI
41GLM 4.7Zhipu1169.1
$0.40
via DeepInfra
$1.75
via DeepInfra
42Nvidia Nemotron 3 Ultra 550B A55bNVIDIA1163.0
$0.50
via DeepInfra
$2.15
via Wandb
43MiniMax M2.7MiniMax1159.8
$0.25
via DeepInfra
$0.55
via Pinstripes
44Muse SparkMeta1146.3
n/a
n/a
45Qwen3.6 PlusAlibaba1140.1
$0.325
Routed quote
$1.95
Routed quote
46Qwen3.6 27BAlibaba1140.0
$0.15
via Libertai
$0.50
via Libertai
47Gemini 3.5 Flash LiteGoogle1139.9
$0.30
via Google
$2.50
via Aihubmix
48Solar Open2 250BUpstage1121.9
n/a
n/a
49A.X-K2Sk-telecom1109.4
n/a
n/a
50inclusionAI: Ling 3.0 FlashOther1107.2
$0.021
Routed quote
$0.063
Routed quote
1–50 of 202
Page 1 of 5
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.

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 Opus 5 (Anthropic) leads with 1844.7, from $5.00 per 1M input tokens from Anthropic. Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

How many models are ranked on GDPval?

202 models carry a GDPval score. Scores come from Artificial Analysis; where a model has a listed API price it is drawn from 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 DiamondleaderboardHumanity's Last ExamleaderboardMMLU-ProleaderboardMMMU-ProleaderboardLiveCodeBenchleaderboardSciCodeleaderboardTerminalBench HardleaderboardTerminalBench v2.1leaderboardτ²-benchleaderboardτ-bench BankingleaderboardAPEX AgentsleaderboardIT-Bench SREleaderboardCritPtleaderboardOmniscienceleaderboardIFBenchleaderboardLong-Context Reasoningcomposite indexSWE-bench VerifiedleaderboardSWE-bench ProleaderboardAIME 2026leaderboardARC-AGI-2leaderboardAA-Briefcaseleaderboard
Benchmark scores via Artificial Analysis · last published Aug 18, 2026 · Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 80 prices older, back to Jul 19, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI