# GDPval-AA leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/agentic-gdpval-aa

Every model the catalog carries a published GDPval-AA value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Elo |
| Tasks | Agentic real-world work tasks |
| Difficulty | Professional agentic workflows |
| Published by | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |

An agentic real-world work-task evaluation reported as an Elo score in DeepSeek-V4 thinking-mode evaluations.

## GDPval-AA ranking

130 models with a published GDPval-AA value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Elo | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 1862 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 1861 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Muse Wonder Full](https://modelchoice.dev/models/muse-wonder-full) | Meta | 1857 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 1846 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 1844 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Fable 5.2](https://modelchoice.dev/models/claude-fable-5-2) | Anthropic | 1831 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Qwen4 Max](https://modelchoice.dev/models/qwen4-max) | Alibaba | 1809 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GLM-5.3-Flash](https://modelchoice.dev/models/glm-5-3-flash) | Z.AI | 1773 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Muse Wonder](https://modelchoice.dev/models/muse-wonder) | Meta | 1770 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GLM-5.3](https://modelchoice.dev/models/glm-5-3) | Z.AI | 1769 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 1765 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Muse Spark 1.3](https://modelchoice.dev/models/muse-spark-1-3) | Meta | 1754 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Claude Fable 5](https://modelchoice.dev/models/claude-fable-5) | Anthropic | 1747 | Observed 2026-11-21 · source benchlm:models |
| 14 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 1735 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Gemini 4 Carbon](https://modelchoice.dev/models/gemini-4-carbon) | Google | 1733 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Grok 4.7](https://modelchoice.dev/models/grok-4-7) | xAI | 1717 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Hy4 preview](https://modelchoice.dev/models/hy4-preview) | Tencent | 1678 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Ling 3.1 Flash](https://modelchoice.dev/models/ling-3-1-flash) | InclusionAI | 1673 | Observed 2026-11-21 · source benchlm:models |
| 18 | [MiMo-V2.6-Pro](https://modelchoice.dev/models/mimo-v2-6-pro) | Xiaomi | 1673 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Qwen3.8-Flash-Next](https://modelchoice.dev/models/qwen3-8-flash-next) | Alibaba | 1648 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Grok 4.6](https://modelchoice.dev/models/grok-4-6) | xAI | 1643 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Muse Spark 1.2](https://modelchoice.dev/models/muse-spark-1-2) | Meta | 1631 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Inkling 2 Small](https://modelchoice.dev/models/inkling-2-small) | Thinking Machines Lab | 1630 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Qwen3.8 Max Preview](https://modelchoice.dev/models/qwen3-8-max-preview) | Alibaba | 1630 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Gemini 4 Argon](https://modelchoice.dev/models/gemini-4-argon) | Google | 1624 | Last good 2026-10-23 · source benchlm:models |
| 26 | [Claude Haiku 5.5](https://modelchoice.dev/models/claude-haiku-5-5) | Anthropic | 1620 | Observed 2026-11-21 · source benchlm:models |
| 27 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 1607 | Last good 2026-11-17 · source benchlm:models |
| 28 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 1603 | Observed 2026-11-21 · source benchlm:models |
| 29 | [DeepSeek V4.1 Flash 1017](https://modelchoice.dev/models/deepseek-v4-1-flash) | DeepSeek | 1600 | Last good 2026-10-08 · source benchlm:models |
| 30 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 1593 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 1584 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Atria Dawn Preview](https://modelchoice.dev/models/atria-dawn-preview) | Shanghai Artificial Intelligence Laboratory | 1583 | Observed 2026-11-21 · source benchlm:models |
| 32 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 1583 | Observed 2026-11-21 · source benchlm:models |
| 34 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 1582 | Observed 2026-11-21 · source benchlm:models |
| 35 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 1580 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Step 5 Preview](https://modelchoice.dev/models/step-5-preview) | StepFun | 1566 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 1545 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Gemini 3.7 Flash](https://modelchoice.dev/models/gemini-3-7-flash) | Google | 1525 | Observed 2026-11-21 · source benchlm:models |
| 39 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 1510 | Last good 2026-10-08 · source benchlm:models |
| 40 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 1476 | Observed 2026-11-21 · source benchlm:models |
| 41 | [MiniMax M3.1 Flash](https://modelchoice.dev/models/minimax-m3-1-flash) | MiniMax | 1458 | Last good 2026-10-23 · source benchlm:models |
| 42 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 1443 | Observed 2026-11-21 · source benchlm:models |
| 43 | [Grok 4.5](https://modelchoice.dev/models/grok-4-5) | xAI | 1430 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Qwen3.8-27B](https://modelchoice.dev/models/qwen3-8-27b) | Alibaba | 1426 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Gemini 3.6 Flash](https://modelchoice.dev/models/gemini-3-6-flash) | Google | 1423 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Mistral Large 4](https://modelchoice.dev/models/mistral-large-4) | Mistral | 1422 | Last good 2026-10-23 · source benchlm:models |
| 47 | [GLM-5.2](https://modelchoice.dev/models/glm-5-2) | Z.AI | 1418 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Muse Spark Open](https://modelchoice.dev/models/muse-spark-open) | Meta | 1401 | Last good 2026-10-23 · source benchlm:models |
| 49 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 1396 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Claude Opus 4.7 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-7-max) | Anthropic | 1396 | Last good 2026-11-18 · source benchlm:models |
| 49 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 1396 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 1375 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 1345 | Observed 2026-11-21 · source benchlm:models |
| 54 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 1307 | Observed 2026-11-21 · source benchlm:models |
| 55 | [DeepSeek V4 Pro](https://modelchoice.dev/models/deepseek-v4-pro) | DeepSeek | 1306 | Observed 2026-11-21 · source benchlm:models |
| 55 | [DeepSeek V4 Pro 0813](https://modelchoice.dev/models/deepseek-v4-pro-max) | DeepSeek | 1306 | Last good 2026-11-18 · source benchlm:models |
| 57 | [MiniMax M3](https://modelchoice.dev/models/minimax-m3) | MiniMax | 1304 | Observed 2026-11-21 · source benchlm:models |
| 58 | [Ling 3.0 Flash Sante](https://modelchoice.dev/models/ling-3-0-flash-sante) | InclusionAI | 1288 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Apodex 1.1](https://modelchoice.dev/models/apodex-1-1) | Apodex | 1273 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Apodex 1.1 Mini](https://modelchoice.dev/models/apodex-1-1-mini) | Apodex | 1273 | Observed 2026-11-21 · source benchlm:models |
| 61 | [MiMo-V2.5-Pro](https://modelchoice.dev/models/mimo-v2-5-pro) | Xiaomi | 1265 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Quasar 438B](https://modelchoice.dev/models/quasar-438b) | Multiverse Computing | 1239 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Nemotron 3.5 Super VL 120B A12B](https://modelchoice.dev/models/nemotron-3-5-super-vl-120b-a12b) | NVIDIA | 1211 | Observed 2026-11-21 · source benchlm:models |
| 64 | [Nemotron 3.5 Super VL 120B A12B NVFP4](https://modelchoice.dev/models/nemotron-3-5-super-vl-120b-a12b-nvfp4) | NVIDIA | 1206 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Inkling-Small](https://modelchoice.dev/models/inkling-small) | Thinking Machines Lab | 1191 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 1190 | Observed 2026-11-21 · source benchlm:models |
| 67 | [DeepSeek V4 Flash 0731](https://modelchoice.dev/models/deepseek-v4-flash-max) | DeepSeek | 1189 | Observed 2026-11-21 · source benchlm:models |
| 68 | [GLM-5.1](https://modelchoice.dev/models/glm-5-1) | Z.AI | 1181 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Beam 1.0 501B-A23B](https://modelchoice.dev/models/reflection-beam) | Reflection AI | 1177 | Observed 2026-11-21 · source benchlm:models |
| 70 | [Inkling](https://modelchoice.dev/models/inkling) | Thinking Machines Lab | 1165 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Gemini 3.5 Flash-Lite](https://modelchoice.dev/models/gemini-3-5-flash-lite) | Google | 1139 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Hy3](https://modelchoice.dev/models/hy3) | Tencent | 1136 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Hy3 Preview](https://modelchoice.dev/models/hy3-preview) | Tencent | 1136 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 1115 | Observed 2026-11-21 · source benchlm:models |
| 75 | [Kimi K2.7 Code](https://modelchoice.dev/models/kimi-k2-7-code) | Moonshot AI | 1114 | Observed 2026-11-21 · source benchlm:models |
| 76 | [Ling 3.0 Flash](https://modelchoice.dev/models/ling-3-0-flash) | InclusionAI | 1107 | Observed 2026-11-21 · source benchlm:models |
| 77 | [GLM-4.7](https://modelchoice.dev/models/glm-4-7) | Z.AI | 1096 | Observed 2026-11-21 · source benchlm:models |
| 78 | [GPT-5.4 mini](https://modelchoice.dev/models/gpt-5-4-mini) | OpenAI | 1095 | Observed 2026-11-21 · source benchlm:models |
| 79 | [Nemotron 3 Ultra](https://modelchoice.dev/models/nemotron-3-ultra-500b) | NVIDIA | 1091 | Observed 2026-11-21 · source benchlm:models |
| 80 | [MiniMax M2.7](https://modelchoice.dev/models/minimax-m2-7) | MiniMax | 1087 | Observed 2026-11-21 · source benchlm:models |
| 81 | [Muse Spark](https://modelchoice.dev/models/muse-spark) | Meta | 1076 | Observed 2026-11-21 · source benchlm:models |
| 82 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 1069 | Observed 2026-11-21 · source benchlm:models |
| 83 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 1066 | Observed 2026-11-21 · source benchlm:models |
| 84 | [Ling 3.0 Flash FP8](https://modelchoice.dev/models/ling-3-0-flash-fp8) | InclusionAI | 1036 | Last good 2026-10-08 · source benchlm:models |
| 85 | [GPT-5.4 nano](https://modelchoice.dev/models/gpt-5-4-nano) | OpenAI | 1035 | Observed 2026-11-21 · source benchlm:models |
| 86 | [Grok 4.3](https://modelchoice.dev/models/grok-4-3) | xAI | 1018 | Observed 2026-11-21 · source benchlm:models |
| 87 | [GPT-5](https://modelchoice.dev/models/gpt-5) | OpenAI | 1015 | Observed 2026-11-21 · source benchlm:models |
| 87 | [GPT-5 (high)](https://modelchoice.dev/models/gpt-5-high) | OpenAI | 1015 | Last good 2026-11-18 · source benchlm:models |
| 89 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 992 | Observed 2026-11-21 · source benchlm:models |
| 90 | [Step 3.7 Flash](https://modelchoice.dev/models/step-3-7-flash) | StepFun | 954 | Observed 2026-11-21 · source benchlm:models |
| 91 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 936 | Observed 2026-11-21 · source benchlm:models |
| 91 | [Kimi K2.5 (Reasoning)](https://modelchoice.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 936 | Last good 2026-11-18 · source benchlm:models |
| 93 | [GPT-5.1](https://modelchoice.dev/models/gpt-5-1) | OpenAI | 930 | Observed 2026-11-21 · source benchlm:models |
| 94 | [Qwen3.5-122B-A10B](https://modelchoice.dev/models/qwen3-5-122b-a10b) | Alibaba | 925 | Observed 2026-11-21 · source benchlm:models |
| 95 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 904 | Observed 2026-11-21 · source benchlm:models |
| 96 | [Muse Glimmer 30B](https://modelchoice.dev/models/muse-glimmer-30b) | Meta | 893 | Observed 2026-11-21 · source benchlm:models |
| 97 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 886 | Observed 2026-11-21 · source benchlm:models |
| 98 | [Mistral Medium 3.5 128B](https://modelchoice.dev/models/mistral-medium-3-5-128b) | Mistral | 875 | Observed 2026-11-21 · source benchlm:models |
| 99 | [Nemotron 3.5 Lightning 30B A3B NVFP4](https://modelchoice.dev/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | 865 | Observed 2026-11-21 · source benchlm:models |
| 100 | [MiMo-V2-Flash](https://modelchoice.dev/models/mimo-v2-flash) | Xiaomi | 788 | Observed 2026-11-21 · source benchlm:models |
| 101 | [Gemma 4 31B](https://modelchoice.dev/models/gemma-4-31b) | Google | 755 | Observed 2026-11-21 · source benchlm:models |
| 102 | [GPT-OSS 120B](https://modelchoice.dev/models/gpt-oss-120b) | OpenAI | 745 | Observed 2026-11-21 · source benchlm:models |
| 103 | [Gemma 4 26B A4B](https://modelchoice.dev/models/gemma-4-26b-a4b) | Google | 713 | Observed 2026-11-21 · source benchlm:models |
| 104 | [Command A+](https://modelchoice.dev/models/command-a-plus) | Cohere | 658 | Observed 2026-11-21 · source benchlm:models |
| 105 | [Granite 4.2 8B](https://modelchoice.dev/models/granite-4-2-8b) | IBM | 646 | Observed 2026-11-21 · source benchlm:models |
| 106 | [Nemotron 3 Super 100B](https://modelchoice.dev/models/nemotron-3-super-100b) | NVIDIA | 644 | Last good 2026-10-08 · source benchlm:models |
| 107 | [Gemini 2.5 Pro](https://modelchoice.dev/models/gemini-2-5-pro) | Google | 616 | Observed 2026-11-21 · source benchlm:models |
| 108 | [Gemma 4 12B](https://modelchoice.dev/models/gemma-4-12b) | Google | 591 | Observed 2026-11-21 · source benchlm:models |
| 109 | [Mistral Large 3](https://modelchoice.dev/models/mistral-large-3) | Mistral | 588 | Observed 2026-11-21 · source benchlm:models |
| 110 | [Ling 2.6 Flash](https://modelchoice.dev/models/ling-2-6-flash) | InclusionAI | 550 | Observed 2026-11-21 · source benchlm:models |
| 111 | [K-Exaone](https://modelchoice.dev/models/k-exaone) | LG AI Research | 540 | Observed 2026-11-21 · source benchlm:models |
| 112 | [Mistral Small 4](https://modelchoice.dev/models/mistral-small-4) | Mistral | 537 | Observed 2026-11-21 · source benchlm:models |
| 112 | [Mistral Small 4 (Reasoning)](https://modelchoice.dev/models/mistral-small-4-reasoning) | Mistral | 537 | Last good 2026-11-18 · source benchlm:models |
| 114 | [GPT-OSS 20B](https://modelchoice.dev/models/gpt-oss-20b) | OpenAI | 514 | Observed 2026-11-21 · source benchlm:models |
| 115 | [Trinity-Large-Preview](https://modelchoice.dev/models/trinity-large-preview) | Arcee AI | 512 | Observed 2026-11-21 · source benchlm:models |
| 115 | [Trinity-Large-Thinking](https://modelchoice.dev/models/trinity-large-thinking) | Arcee AI | 512 | Observed 2026-11-21 · source benchlm:models |
| 117 | [Celeris-1](https://modelchoice.dev/models/celeris-1) | Celeris | 483 | Observed 2026-11-21 · source benchlm:models |
| 118 | [GPT-4.1 mini](https://modelchoice.dev/models/gpt-4-1-mini) | OpenAI | 453 | Observed 2026-11-21 · source benchlm:models |
| 119 | [Nemotron 3 Nano 30B](https://modelchoice.dev/models/nemotron-3-nano-30b) | NVIDIA | 438 | Observed 2026-11-21 · source benchlm:models |
| 120 | [Nemotron 3 Nano Omni 30B A3B](https://modelchoice.dev/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 416 | Observed 2026-11-21 · source benchlm:models |
| 121 | [LFM2.5-2.6B](https://modelchoice.dev/models/lfm2-5-2-6b) | LiquidAI | 202 | Observed 2026-11-21 · source benchlm:models |
| 122 | [GPT-4o mini](https://modelchoice.dev/models/gpt-4o-mini) | OpenAI | 188 | Observed 2026-11-21 · source benchlm:models |
| 123 | [DeepSeek V3](https://modelchoice.dev/models/deepseek-v3) | DeepSeek | 183 | Observed 2026-11-21 · source benchlm:models |
| 124 | [Gemma 4 E4B](https://modelchoice.dev/models/gemma-4-e4b) | Google | 177 | Observed 2026-11-21 · source benchlm:models |
| 125 | [Llama 4 Scout](https://modelchoice.dev/models/llama-4-scout) | Meta | 60 | Observed 2026-11-21 · source benchlm:models |
| 126 | [Ultravox v0.6 Llama 3.3 70B](https://modelchoice.dev/models/ultravox-v0-6-llama-3-3-70b) | Fixie AI | 50 | Observed 2026-11-21 · source benchlm:models |
| 127 | [Gemma 4 E2B](https://modelchoice.dev/models/gemma-4-e2b) | Google | 36 | Observed 2026-11-21 · source benchlm:models |
| 128 | [GPT-4.1 nano](https://modelchoice.dev/models/gpt-4-1-nano) | OpenAI | 13 | Observed 2026-11-21 · source benchlm:models |
| 129 | [Llama 4 Maverick](https://modelchoice.dev/models/llama-4-maverick) | Meta | -45 | Observed 2026-11-21 · source benchlm:models |
| 130 | [Gemma 3 27B](https://modelchoice.dev/models/gemma-3-27b) | Google | -171 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
