# GDPval-AA normalized (GDPval-AA)

> A display-only Artificial Analysis normalized score for economically valuable tasks.

Canonical page: https://benchlm.ai/benchmarks/gdpvalaanormalized

- Category: [Agentic](/agentic)
- Last updated: September 15, 2026

## About GDPval-AA

- Year: 2026
- Tasks: Economically valuable tasks
- Format: Normalized score
- Difficulty: Professional agentic workflows
- Paper: [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3)

OpenRouter's Grok 4.3 benchmark card displays GDPval-AA as a normalized percentage. BenchLM stores it separately from the Elo-style GDPval-AA rows used in provider comparison tables.

GDPval-AA is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (108 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 63.2% |
| 2 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 61.8% |
| 3 | [Muse Spark 1.3](/models/muse-spark-1-3) | Meta | 60.2% |
| 4 | [GLM-5.3](/models/glm-5-3) | Z.AI | 57.8% |
| 5 | [Qwen3.8-Flash-Next](/models/qwen3-8-flash-next) | Alibaba | 57.4% |
| 6 | [Grok 4.6](/models/grok-4-6) | xAI | 57.1% |
| 7 | [Claude Fable 5](/models/claude-fable) | Anthropic | 56.6% |
| 8 | [DeepSeek V4.1 Flash](/models/deepseek-v4-1-flash) | DeepSeek | 56.6% |
| 9 | [Qwen3.8 Max Preview](/models/qwen3-8-max-preview) | Alibaba | 56.5% |
| 10 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | 56.2% |
| 11 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | 54.5% |
| 12 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 54.0% |
| 13 | [Kimi K3](/models/kimi-k3) | Moonshot AI | 52.6% |
| 14 | [Muse Spark 1.2](/models/muse-spark-1-2) | Meta | 51.2% |
| 15 | [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | 50.0% |
| 16 | [Claude Opus 4.8](/models/claude-opus-4-8) | Anthropic | 49.5% |
| 17 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | OpenAI | 48.8% |
| 18 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | 48.2% |
| 19 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | 48.2% |
| 20 | [Qwen3.8-27B](/models/qwen3-8-27b) | Alibaba | 48.2% |
| 21 | [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) | DeepSeek | 47.8% |
| 22 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | 46.7% |
| 23 | [Grok 4.5](/models/grok-4-5) | xAI | 46.5% |
| 24 | [GLM-5.2](/models/glm-5-2) | Z.AI | 45.3% |
| 25 | [GPT-5.5](/models/gpt-5-5) | OpenAI | 44.8% |
| 26 | [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) | Anthropic | 44.8% |
| 27 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | 42.2% |
| 28 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | Google | 41.6% |
| 29 | [GPT-5.4](/models/gpt-5-4) | OpenAI | 40.3% |
| 30 | [MiniMax M3](/models/minimax-m3) | MiniMax | 40.2% |
| 31 | [Muse Spark 1.1](/models/muse-spark-1-1) | Meta | 39.7% |
| 32 | [Apodex 1.1](/models/apodex-1-1) | Apodex | 38.7% |
| 33 | [Apodex 1.1 Mini](/models/apodex-1-1-mini) | Apodex | 38.7% |
| 34 | [Quasar 438B](/models/quasar-438b) | Multiverse Computing | 37.0% |
| 35 | [Ling 3.0 Flash VL](/models/ling-3-0-flash-vl) | InclusionAI | 36.2% |
| 36 | [Hy3 Preview](/models/hy3-preview) | Tencent | 35.8% |
| 37 | [Inkling-Small](/models/inkling-small) | Thinking Machines Lab | 34.6% |
| 38 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | 34.5% |
| 39 | [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | Xiaomi | 34.3% |
| 40 | [GLM-5.1](/models/glm-5-1) | Z.AI | 34.0% |
| 41 | [Solar Pro 4](/models/solar-pro-4) | Upstage | 33.6% |
| 42 | [Inkling](/models/inkling) | Thinking Machines Lab | 33.3% |
| 43 | [Nemotron 3 Ultra](/models/nemotron-3-ultra) | NVIDIA | 33.1% |
| 44 | [Hy3](/models/hy3) | Tencent | 31.8% |
| 45 | [Kimi K2.7 Code](/models/kimi-k2-7-code) | Moonshot AI | 30.7% |
| 46 | [Kimi K2.6](/models/kimi-2-6) | Moonshot AI | 29.8% |
| 47 | [GLM-4.7](/models/glm-4-7) | Z.AI | 29.8% |
| 48 | [GPT-5.4 mini](/models/gpt-5-4-mini) | OpenAI | 29.7% |
| 49 | [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | 29.4% |
| 50 | [Grok 4.3](/models/grok-4-3) | xAI | 29.2% |
| 51 | [Muse Spark](/models/muse-spark) | Meta | 28.8% |
| 52 | [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | 28.4% |
| 53 | [Qwen3.6 Plus](/models/qwen3-6-plus) | Alibaba | 28.3% |
| 54 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | 28.2% |
| 55 | [A.X K2](/models/a-x-k2) | SK Telecom | 27.2% |
| 56 | [GPT-5.4 nano](/models/gpt-5-4-nano) | OpenAI | 26.8% |
| 57 | [Ling 3.0 Flash](/models/ling-3-0-flash) | InclusionAI | 25.9% |
| 58 | [Ling 3.0 Flash FP8](/models/ling-3-0-flash-fp8) | InclusionAI | 25.9% |
| 59 | [Step 3.7 Flash](/models/step-3-7-flash) | StepFun | 25.8% |
| 60 | [GPT-5 (high)](/models/gpt-5-high) | OpenAI | 25.7% |
| 61 | [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) | Alibaba | 24.5% |
| 62 | [Kimi K2.5 (Reasoning)](/models/kimi-k2-5-reasoning) | Moonshot AI | 21.8% |
| 63 | [Kimi K2.5](/models/kimi-k2-5) | Moonshot AI | 21.8% |
| 64 | [GPT-5.1](/models/gpt-5-1) | OpenAI | 21.5% |
| 65 | [Qwen3.5-122B-A10B](/models/qwen3-5-122b-a10b) | Alibaba | 21.3% |
| 66 | [K-EXAONE 2.0](/models/k-exaone-2-0) | LG AI Research | 20.9% |
| 67 | [Gemini 3.1 Pro](/models/gemini-3-1-pro) | Google | 20.2% |
| 68 | [Muse Glimmer 30B](/models/muse-glimmer-30b) | Meta | 19.6% |
| 69 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | 19.3% |
| 70 | [Mistral Medium 3.5 128B](/models/mistral-medium-3-5-128b) | Mistral | 18.8% |
| 71 | [MiniCPM5-2B](/models/minicpm5-2b) | OpenBMB | 16.4% |
| 72 | [MiMo-V2-Flash](/models/mimo-v2-flash) | Xiaomi | 14.4% |
| 73 | [Nemotron 3.5 Lightning 30B A3B NVFP4](/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | 13.3% |
| 74 | [Gemma 4 31B](/models/gemma-4-31b) | Google | 12.8% |
| 75 | [GPT-OSS 120B](/models/gpt-oss-120b) | OpenAI | 12.2% |
| 76 | [Granite 4.2 30B](/models/granite-4-2-30b) | IBM | 11.1% |
| 77 | [Ling 3.0 Tiny](/models/ling-3-0-tiny) | InclusionAI | 10.8% |
| 78 | [Gemma 4 26B A4B](/models/gemma-4-26b-a4b) | Google | 10.7% |
| 79 | [Command A+](/models/command-a-plus) | Cohere | 7.9% |
| 80 | [Granite 4.2 8B](/models/granite-4-2-8b) | IBM | 7.3% |
| 81 | [Nemotron 3 Super 100B](/models/nemotron-3-super-100b) | NVIDIA | 7.2% |
| 82 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | 5.8% |
| 83 | [Gemma 4 12B](/models/gemma-4-12b) | Google | 4.5% |
| 84 | [Mistral Large 3](/models/mistral-large-3) | Mistral | 4.4% |
| 85 | [K-Exaone](/models/k-exaone) | LG AI Research | 2.0% |
| 86 | [Mistral Small 4](/models/mistral-small-4) | Mistral | 1.8% |
| 87 | [Mistral Small 4 (Reasoning)](/models/mistral-small-4-reasoning) | Mistral | 1.8% |
| 88 | [GPT-OSS 20B](/models/gpt-oss-20b) | OpenAI | 0.7% |
| 89 | [Trinity-Large-Preview](/models/trinity-large-preview) | Arcee AI | 0.6% |
| 90 | [Trinity-Large-Thinking](/models/trinity-large-thinking) | Arcee AI | 0.6% |
| 91 | [Nemotron 3 Nano 30B](/models/nemotron-3-nano-30b) | NVIDIA | 0.0% |
| 92 | [DeepSeek V3](/models/deepseek-v3) | DeepSeek | 0.0% |
| 93 | [Nemotron 3 Nano Omni 30B A3B](/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 0.0% |
| 94 | [Ling 2.6 Flash](/models/ling-2-6-flash) | InclusionAI | 0.0% |
| 95 | [Gemma 4 E4B](/models/gemma-4-e4b) | Google | 0.0% |
| 96 | [LFM2.5-2.6B](/models/lfm2-5-2-6b) | LiquidAI | 0.0% |
| 97 | [Gemma 4 E2B](/models/gemma-4-e2b) | Google | 0.0% |
| 98 | [Gemma 3 27B](/models/gemma-3-27b) | Google | 0.0% |
| 99 | [GPT-4.1 mini](/models/gpt-4-1-mini) | OpenAI | 0.0% |
| 100 | [Llama 4 Scout](/models/llama-4-scout) | Meta | 0.0% |
| 101 | [GPT-4o mini](/models/gpt-4o-mini) | OpenAI | 0.0% |
| 102 | [GPT-4.1 nano](/models/gpt-4-1-nano) | OpenAI | 0.0% |
| 103 | [Llama 4 Maverick](/models/llama-4-maverick) | Meta | 0.0% |
| 104 | [Celeris-1](/models/celeris-1) | Celeris | 0.0% |
| 105 | [Solar Pro 3](/models/solar-pro-3) | Upstage | 0.0% |
| 106 | [Granite 4.2 3B](/models/granite-4-2-3b) | IBM | 0.0% |
| 107 | [North Mini Code](/models/north-mini-code-1-0) | Cohere | 0.0% |
| 108 | [Ultravox v0.6 Llama 3.3 70B](/models/ultravox-v0-6-llama-3-3-70b) | Fixie AI | 0.0% |

## FAQ

### What does GDPval-AA measure?

A display-only Artificial Analysis normalized score for economically valuable tasks.

### Which model scores highest on GDPval-AA?

Claude Fable 5.1 by Anthropic currently leads with a score of 63.2% on GDPval-AA.

### How many models are evaluated on GDPval-AA?

108 AI models have been evaluated on GDPval-AA on BenchLM.

### Does GDPval-AA affect BenchLM's overall score?

Not directly. GDPval-AA is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on GDPval-AA

- [Claude Fable 5.1 vs Claude Opus 5](/compare/claude-fable-5-1-vs-claude-opus-5)
- [Claude Opus 5 vs Muse Spark 1.3](/compare/claude-opus-5-vs-muse-spark-1-3)
- [Muse Spark 1.3 vs GLM-5.3](/compare/glm-5-3-vs-muse-spark-1-3)
- [GLM-5.3 vs Qwen3.8-Flash-Next](/compare/glm-5-3-vs-qwen3-8-flash-next)