BlogLLM Benchmark Scores as Published, Side by Side

GDPval-AA: Results as Published

Every result the catalog holds for GDPval-AA: 72 models from 14 developers, read from 36 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.

Area Knowledge WorkMaintainer Artificial Analysis, which runs its own version of OpenAI's GDPval datasetData version 2026103001, as of 2026-10-30

GDPval-AA is Artificial Analysis's version of OpenAI's GDPval, a set of realistic work tasks drawn from 44 occupations in nine major industries. Models get shell access and web browsing in an agent loop and produce a work product, and the outputs are compared in blind pairwise judgments that are turned into Elo ratings. The v2 revision re-anchors the scale so that human-expert deliverables sit near 1000 points.

GDPval-AA v2

ModelValuePrinted bySetup as printed
GPT-5.6 LunaOpenAI, released 2026-07-091591.8OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 1 more page-
GPT-5.6 SolOpenAI, released 2026-07-091747.8OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 8 more pages-
GPT-5.6 TerraOpenAI, released 2026-07-091593OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 3 more pages-
GPT-5.5OpenAI, released 2026-04-231493.7OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 1 more page-
GPT-5.4 miniOpenAI, released 2026-03-171171Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15-
Claude Fable 5.1Anthropic, released 2026-09-011853Anthropic, Claude Fable 5.1 and Mythos 5.1checked 2026-10-15; printed on 1 more page-
Claude Opus 5Anthropic, released 2026-07-241861Anthropic, Claude Opus 5checked 2026-10-15; printed on 3 more pages-
Claude Sonnet 5Anthropic, released 2026-06-301618Anthropic, Claude Sonnet 5checked 2026-10-15; printed on 3 more pages-
Claude Fable 5Anthropic, released 2026-06-091723Anthropic, Claude Fable 5.1 and Mythos 5.1checked 2026-10-15; printed on 7 more pages-
Claude Opus 4.8Anthropic, released 2026-05-281593Anthropic, Claude Opus 5checked 2026-10-15; printed on 5 more pages-
Claude Sonnet 4.6Anthropic, released 2026-02-171395Anthropic, Claude Sonnet 5checked 2026-10-15-
Claude Haiku 4.5Anthropic, released 2025-10-15907Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15-
Gemini 3.8 FlashGoogle, released 2026-09-021545Google, Gemini 3.8 Flash model cardchecked 2026-10-15-
Gemini 3.7 FlashGoogle, released 2026-08-131525Google, Gemini 3.7 Flash model cardchecked 2026-10-15; printed on 2 more pages-
Gemini 3.5 Flash-LiteGoogle, released 2026-07-211140Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15-
Gemini 3.6 FlashGoogle, released 2026-07-211421Google, Gemini 3.6 Flash model cardchecked 2026-10-15; printed on 1 more page-
Gemini 3.5 FlashGoogle, released 2026-05-191349Google, Gemini 3.6 Flash model cardchecked 2026-10-15; printed on 1 more page-
Gemma 4 26B A4BGoogle, released 2026-04-02807NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19-
Gemini 3.1 Flash-LiteGoogle, released 2026-03-03642Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15-
Gemini 3.1 Pro PreviewGoogle, released 2026-02-19965Google, Gemini 3.6 Flash model cardchecked 2026-10-15; printed on 2 more pages-
Grok 4.6xAI, released 2026-08-121753xAI, Introducing Grok 4.6checked 2026-10-15Effort: high
Grok 4.5xAI, released 2026-07-161526xAI, Introducing Grok 4.6checked 2026-10-15; printed on 1 more pageEffort: high
Muse Spark OpenMeta, released 2026-10-151401Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19Effort: xhigh
Muse Spark 1.2Meta, released 2026-08-051628Google, Gemini 3.7 Flash model cardchecked 2026-10-15-
DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-241307Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15-
DeepSeek-V4-Flash-0731DeepSeek1382NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19-
DeepSeek-V4-Pro-0813DeepSeek1590Z.ai, GLM-5.3 model cardchecked 2026-10-15-
DeepSeek-V4-Vision-ExpDeepSeek1675Z.ai, Z.ai GLM-5.3-Flash model cardchecked 2026-10-15-
Qwen3.8-MaxAlibaba, released 2026-08-031739Z.ai, GLM-5.3 model cardchecked 2026-10-15-
Qwen3.6-35B-A3BAlibaba, released 2026-04-161015NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19-
Qwen3.5-122B-A10BAlibaba, released 2026-02-24861NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19-
Qwen3.8-2.4T-A95BAlibaba1613Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19Effort: xhigh
Qwen3.8-Flash-NextAlibaba1561NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19-
Kimi K3Moonshot AI, released 2026-07-161686Moonshot AI, Kimi K3 model cardchecked 2026-10-15; printed on 2 more pagesEffort: max
Kimi K2.6Moonshot AI, released 2026-04-201190Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15-
Kimi K2.5Moonshot AI, released 2026-01-271009Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15-
GLM-5.3-FlashZ.ai, released 2026-08-261773Z.ai, Z.ai GLM-5.3-Flash model cardchecked 2026-10-15; printed on 1 more pageEffort: max
GLM-5.3Z.ai, released 2026-08-181769Z.ai, GLM-5.3 model cardchecked 2026-10-15; printed on 1 more pageEffort: max
GLM-5.2Z.ai, released 2026-06-161508Z.ai, GLM-5.3 model cardchecked 2026-10-15; printed on 3 more pages-
Mistral Large 4 (preview)Mistral AI, released 2026-10-061424Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19-
Nemotron 3.5 Super VL 120B-A12BNVIDIA, released 2026-10-151211NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19-
Nemotron 3.5 Lightning 30B-A3BNVIDIA, released 2026-08-11832NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19-
Nemotron 3 UltraNVIDIA, released 2026-06-041148NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19; printed on 2 more pages-
Nemotron 3 SuperNVIDIA, released 2026-03-11746NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19-
Nemotron 3 Nano 30B-A3BNVIDIA, released 2025-12-15473NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19-
InklingThinking Machines, released 2026-07-141233Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15; printed on 1 more pageEffort: 0.99
Inkling-SmallThinking Machines1313NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19-

GDPval-AA (Elo)

ModelValuePrinted bySetup as printed
GPT-5.6 LunaOpenAI, released 2026-07-091569IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15Effort: max
GPT-5.6 TerraOpenAI, released 2026-07-091503IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15Effort: high
GPT-5.5OpenAI, released 2026-04-231769Anthropic, Claude Fable 5 and Claude Mythos 5checked 2026-10-15; printed on 2 more pages-
GPT-5.4OpenAI, released 2026-03-051674DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: xhigh
GPT-5.2OpenAI, released 2025-12-111462Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 2 more pages-
Claude Sonnet 5Anthropic, released 2026-06-301584IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15Effort: max
Claude Mythos 5Anthropic, released 2026-06-091932Anthropic, Claude Fable 5 and Claude Mythos 5checked 2026-10-15-
Claude Opus 4.8Anthropic, released 2026-05-281890Anthropic, Claude Opus 4.8checked 2026-10-15; printed on 1 more page-
Claude Opus 4.7Anthropic, released 2026-04-161753Anthropic, Claude Opus 4.8checked 2026-10-15; printed on 1 more page-
Claude Sonnet 4.6Anthropic, released 2026-02-171633Anthropic, Claude Sonnet 4.6checked 2026-10-15; printed on 2 more pages-
Claude Opus 4.6Anthropic, released 2026-02-051606Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 3 more pages-
Claude Opus 4.5Anthropic, released 2025-11-241416Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 1 more page-
Claude Sonnet 4.5Anthropic, released 2025-09-291277Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 1 more page-
Gemini 3.5 FlashGoogle, released 2026-05-191656Google, Gemini 3.5 Flash model cardchecked 2026-10-15-
Gemini 3.1 Pro PreviewGoogle, released 2026-02-191317Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 4 more pagesEffort: high
Gemini 3 FlashGoogle, released 2025-12-171204Google, Gemini 3.5 Flash model cardchecked 2026-10-15-
Gemini 3 ProGoogle, released 2025-11-181195Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 2 more pagesEffort: high
DeepSeek-V4-Flash (Preview)DeepSeek, released 2026-04-241395DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: max
DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-241554DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: max
Kimi K2.6Moonshot AI, released 2026-04-201482DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: thinking
GLM-5.2Z.ai, released 2026-06-161498IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15Effort: max
GLM-5.1Z.ai, released 2026-04-071535DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: thinking
MiniMax M3MiniMax, released 2026-06-011380IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15-
MiniMax M2.7MiniMax, released 2026-03-181495MiniMax, MiniMax-M2.7 model cardchecked 2026-10-15-
Nemotron 3 UltraNVIDIA, released 2026-06-041162IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15-
InklingThinking Machines, released 2026-07-141234IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15Effort: xhigh

GDPval-AA v2.1

ModelValuePrinted bySetup as printed
GPT-6 LunaOpenAI, released 2026-09-221437Anthropic, Claude Haiku 5.5checked 2026-10-15; printed on 1 more page-
GPT-6 SolOpenAI, released 2026-09-221487Anthropic, Claude Sonnet 5.5checked 2026-10-14; printed on 1 more page-
GPT-6 AstraOpenAI, released 2026-09-031542Anthropic, Claude Opus 5.5checked 2026-10-14; printed on 3 more pages-
GPT-5.6 SolOpenAI, released 2026-07-091588Anthropic, Claude Opus 5.5checked 2026-10-14; printed on 1 more page-
Claude Haiku 5.5Anthropic, released 2026-10-071620Anthropic, Claude Haiku 5.5checked 2026-10-15; printed on 1 more page-
Claude Sonnet 5.5Anthropic, released 2026-09-281844Anthropic, Claude Sonnet 5.5checked 2026-10-14; printed on 3 more pages-
Claude Opus 5.5Anthropic, released 2026-09-221846Anthropic, Claude Opus 5.5checked 2026-10-14; printed on 4 more pages-
Claude Fable 5.1Anthropic, released 2026-09-011735Anthropic, Claude Opus 5.5checked 2026-10-14; printed on 4 more pages-
Claude Opus 5Anthropic, released 2026-07-241708Anthropic, Claude Opus 5.5checked 2026-10-14; printed on 2 more pages-
Claude Sonnet 5Anthropic, released 2026-06-301449Anthropic, Claude Sonnet 5.5checked 2026-10-14; printed on 1 more page-
Claude Fable 5Anthropic, released 2026-06-091595Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19-
Claude Haiku 4.5Anthropic, released 2025-10-15735Anthropic, Claude Haiku 5.5checked 2026-10-15; printed on 1 more page-
Grok 4.7xAI, released 2026-09-211695xAI, Grok 4.7checked 2026-10-25Effort: xhigh
Grok 4.6xAI, released 2026-08-121605xAI, Grok 4.7checked 2026-10-25Effort: high
DeepSeek-V4.1-Flash-1017DeepSeek, released 2026-10-171746Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24Effort: max
Kimi K3.1 ProMoonshot AI, released 2026-10-231846Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24Effort: max
GLM-5.3Z.ai, released 2026-08-181650Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24Effort: max
MiMo-V2.6-ProXiaomi, released 2026-09-211673Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19-
MiMo-V2.5-ProXiaomi, released 2026-04-271107Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19-

GDPval-AA v2 (printed as a percentage)

ModelValuePrinted bySetup as printed
Gemma 4 26B A4BGoogle, released 2026-04-0215.33%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19-
Qwen3.6-35B-A3BAlibaba, released 2026-04-1625.75%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19-
Nemotron 3.5 Bolt 74B-A9BNVIDIA, released 2026-10-1528.47%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19Model as printed: Nemotron 3.5 Bolt 74B-A9B-24GB (IQ2)
31.13%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19Model as printed: Nemotron 3.5 Bolt 74B-A9B (BF16)
Nemotron 3.5 Lightning 30B-A3BNVIDIA, released 2026-08-1118.26%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19-

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.