BlogLLM Benchmark Scores as Published, Side by Side

GPQA Diamond: Results as Published

Every result the catalog holds for GPQA Diamond: 141 models from 15 developers, read from 58 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 Science and MathMaintainer David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael and Samuel R. BowmanIntroduced 2023Data version 2026103001, as of 2026-10-30

GPQA is a set of 448 multiple-choice questions in biology, physics and chemistry, written by experts with or working toward PhDs in those fields. Domain experts reached about 65% accuracy, while skilled non-experts with web access reached about 34%, which is why the questions are described as hard to answer by search alone. The Diamond subset is a smaller, harder selection of these questions.

GPQA Diamond

ModelValuePrinted bySetup as printed
GPT-6 AstraOpenAI, released 2026-09-0396%OpenAI, GPT-6 Astrachecked 2026-10-14; printed on 1 more page-
GPT-5.6 LunaOpenAI, released 2026-07-0992.3%OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 1 more page-
GPT-5.6 SolOpenAI, released 2026-07-0994.6%OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 5 more pages-
GPT-5.6 TerraOpenAI, released 2026-07-0992.9%OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 1 more page-
GPT-5.5OpenAI, released 2026-04-2393.6%OpenAI, Introducing GPT-5.5checked 2026-10-15; printed on 3 more pagesEffort: xhigh
GPT-5.4 miniOpenAI, released 2026-03-1788%OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15Effort: xhigh
GPT-5.4 nanoOpenAI, released 2026-03-1782.8%OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15Effort: xhigh
GPT-5.4OpenAI, released 2026-03-0592.8%OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 6 more pagesEffort: xhigh
GPT-5.4 ProOpenAI, released 2026-03-0594.4%OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 2 more pagesEffort: xhigh
GPT-5.3-CodexOpenAI, released 2026-02-0592.6%OpenAI, Introducing GPT-5.4checked 2026-10-15Effort: xhigh
GPT-5.2OpenAI, released 2025-12-1192.4%OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 6 more pagesEffort: xhigh; Tools: none
GPT-5.2 ProOpenAI, released 2025-12-1193.2%OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 3 more pagesEffort: xhigh; Tools: none
GPT-5.1OpenAI, released 2025-11-1288.1%OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 3 more pagesEffort: high; Tools: none
GPT-5OpenAI, released 2025-08-0777.8%OpenAI, Introducing GPT-5checked 2026-10-15; printed on 5 more pagesEffort: none; Tools: no tools
87.3%OpenAI, Introducing GPT-5checked 2026-10-15Effort: high; Tools: python
85.7%OpenAI, Introducing GPT-5checked 2026-10-15Effort: high; Tools: no tools
GPT-5 miniOpenAI, released 2025-08-0781.6%OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15; printed on 1 more pageEffort: high
GPT-5 ProOpenAI, released 2025-08-0789.4%OpenAI, Introducing GPT-5checked 2026-10-15Effort: high; Tools: python
88.4%OpenAI, Introducing GPT-5checked 2026-10-15Effort: high; Tools: no tools
gpt-oss-120bOpenAI, released 2025-08-0580.1%Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15-
gpt-oss-20bOpenAI, released 2025-08-0571.46%NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19Tools: none
o3OpenAI, released 2025-04-1683.3%OpenAI, Introducing GPT-5checked 2026-10-15; printed on 2 more pagesEffort: high; Tools: no tools
GPT-4.1OpenAI, released 2025-04-1466.3%Anthropic, Claude Opus 4 and Claude Sonnet 4checked 2026-10-15; printed on 1 more page-
GPT-4.5OpenAI, released 2025-02-2771.4%DeepSeek, DeepSeek-V3-0324 model cardchecked 2026-10-15-
o3-miniOpenAI, released 2025-01-3179.7%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more pageEffort: high
o1OpenAI, released 2024-12-1775.7%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page-
78%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15Attempt budget: majority voting, N=64 samples (note 3)
o1-miniOpenAI, released 2024-09-1260%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15Model as printed: OpenAI o1-mini
60%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15Model as printed: o1-mini
GPT-4oOpenAI, released 2024-05-1370.1%OpenAI, Introducing GPT-5checked 2026-10-15; printed on 2 more pagesTools: no tools
Claude Opus 5.5Anthropic, released 2026-09-2293.9%Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24Effort: max; Fallback: with fallback
Claude Fable 5.1Anthropic, released 2026-09-0193.7%Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24; printed on 1 more pageEffort: max; Fallback: with fallback
Claude Opus 5Anthropic, released 2026-07-2493.4%DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page-
Claude Sonnet 5Anthropic, released 2026-06-3091.1%IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15Effort: max
Claude Fable 5Anthropic, released 2026-06-0992.6%Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 4 more pages-
Claude Mythos 5Anthropic, released 2026-06-0994.1%OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15-
Claude Opus 4.8Anthropic, released 2026-05-2892%Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 3 more pages-
Claude Opus 4.7Anthropic, released 2026-04-1694.2%Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page-
Claude Mythos PreviewAnthropic, released 2026-04-0794.6%Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page-
Claude Sonnet 4.6Anthropic, released 2026-02-1789.9%Anthropic, Claude Sonnet 4.6checked 2026-10-15; printed on 2 more pages-
Claude Opus 4.6Anthropic, released 2026-02-0591.3%Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 10 more pages-
Claude Opus 4.5Anthropic, released 2025-11-2487%Anthropic, Claude Opus 4.5checked 2026-10-15; printed on 7 more pagesEffort: high
Claude Haiku 4.5Anthropic, released 2025-10-1573%Anthropic, Claude Haiku 4.5checked 2026-10-15Effort: thinking budget 128K
Claude Sonnet 4.5Anthropic, released 2025-09-2983.4%Anthropic, Claude Sonnet 4.5checked 2026-10-15; printed on 7 more pages-
Claude Opus 4.1Anthropic, released 2025-08-0580.9%Anthropic, Claude Opus 4.1checked 2026-10-15; printed on 2 more pagesEffort: extended thinking, up to 64K
Claude Opus 4Anthropic, released 2025-05-2283.3%Anthropic, Claude Opus 4 and Claude Sonnet 4checked 2026-10-15; printed on 2 more pagesEffort: extended thinking, up to 64K; Attempt budget: parallel test-time compute: multiple samples, the best selected by an internal scoring model
74.9%Anthropic, Claude Opus 4 and Claude Sonnet 4checked 2026-10-15Effort: none
79.6%Anthropic, Claude Opus 4 and Claude Sonnet 4checked 2026-10-15Effort: extended thinking, up to 64K
Claude Sonnet 4Anthropic, released 2025-05-2276.1%Anthropic, Claude Sonnet 4.5checked 2026-10-15; printed on 4 more pages-
Claude 3.7 SonnetAnthropic, released 2025-02-2478.2%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 3 more pagesEffort: extended thinking, 64K
68%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15Effort: none
84.8%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15Effort: extended thinking, 64K; Attempt budget: parallel test-time compute: multiple samples, the best selected by an internal scoring model
Claude 3.5 SonnetAnthropic, released 2024-10-2265%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page-
Gemini 3.8 FlashGoogle, released 2026-09-0295.3%OpenAI, GPT-6 Astrachecked 2026-10-14-
Gemma 4 12BGoogle, released 2026-04-0278.8%Google, Gemma 4 model cardchecked 2026-10-15-
Gemma 4 26B A4BGoogle, released 2026-04-0282.3%Google, Gemma 4 model cardchecked 2026-10-15; printed on 3 more pages-
Gemma 4 31BGoogle, released 2026-04-0284.3%Google, Gemma 4 model cardchecked 2026-10-15; printed on 2 more pages-
Gemma 4 E2BGoogle, released 2026-04-0243.4%Google, Gemma 4 model cardchecked 2026-10-15-
Gemma 4 E4BGoogle, released 2026-04-0258.6%Google, Gemma 4 model cardchecked 2026-10-15-
Gemini 3.1 Pro PreviewGoogle, released 2026-02-1994.3%Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 8 more pagesEffort: high; Tools: none
Gemini 3 ProGoogle, released 2025-11-1891.9%Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 8 more pagesEffort: high; Tools: none
Gemini 2.5 FlashGoogle, released 2025-05-2082.8%DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15; printed on 1 more pageEffort: thinking
Gemini 2.5 ProGoogle, released 2025-03-2583%Anthropic, Claude Opus 4 and Claude Sonnet 4checked 2026-10-15; printed on 3 more pages-
Gemma 3 27BGoogle, released 2025-03-1242.4%Google, Gemma 4 model cardchecked 2026-10-15Effort: no think
Grok 4.7xAI, released 2026-09-2192.7%Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30Effort: xhigh
Grok 4xAI, released 2025-07-0987.5%Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15Tools: none
Grok 3xAI, released 2025-02-1780.2%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15Effort: extended thinking
84.6%Anthropic, Claude 3.7 Sonnetchecked 2026-10-15Effort: extended thinking; Attempt budget: majority voting, N=64 samples (note 3)
Muse Spark OpenMeta, released 2026-10-1589%Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19Effort: xhigh
Muse Glimmer-30BMeta, released 2026-08-0983.5%Alibaba, Qwen3.8-27B model cardchecked 2026-10-15-
Llama 4 MaverickMeta, released 2025-04-0569.8%Meta, Meta Llama 4 model cardchecked 2026-10-15; printed on 1 more page-
Llama 4 ScoutMeta, released 2025-04-0557.2%Meta, Meta Llama 4 model cardchecked 2026-10-15-
Llama 3.3 70BMeta, released 2024-12-0650.5%Meta, Meta Llama 4 model cardchecked 2026-10-15-
Llama 3.1 405BMeta, released 2024-07-2349%Meta, Meta Llama 4 model cardchecked 2026-10-15-
DeepSeek-V4.1-Flash-1017DeepSeek, released 2026-10-1792.2%Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24Effort: max
DeepSeek-V4.1-FlashDeepSeek, released 2026-09-1090.9%DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15Effort: max
DeepSeek-V4-Flash (Preview)DeepSeek, released 2026-04-2487.4%DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: high
88.1%DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: max
71.2%DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: non-think
DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-2472.9%DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 3 more pagesEffort: non-think
90.1%DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: max
89.1%DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15Effort: high
DeepSeek-V3.2DeepSeek, released 2025-12-0182.4%Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19; printed on 4 more pages-
DeepSeek-V3.2-ExpDeepSeek, released 2025-09-2979.9%DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more pageTools: none
DeepSeek-V3.1-TerminusDeepSeek, released 2025-09-2280.7%DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15; printed on 1 more pageTools: none
DeepSeek-V3.1DeepSeek, released 2025-08-2180.1%DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15Tools: none
DeepSeek-R1-0528DeepSeek, released 2025-05-2881%DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15-
DeepSeek-R1-0528-Qwen3-8BDeepSeek, released 2025-05-2861.1%DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15-
DeepSeek-V3-0324DeepSeek, released 2025-03-2468.4%DeepSeek, DeepSeek-V3-0324 model cardchecked 2026-10-15; printed on 2 more pages-
DeepSeek-R1DeepSeek, released 2025-01-2071.5%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15; printed on 3 more pages-
DeepSeek-R1-Distill-Llama-70BDeepSeek, released 2025-01-2065.2%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15-
DeepSeek-R1-Distill-Llama-8BDeepSeek, released 2025-01-2049%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15-
DeepSeek-R1-Distill-Qwen-1.5BDeepSeek, released 2025-01-2033.8%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15-
DeepSeek-R1-Distill-Qwen-14BDeepSeek, released 2025-01-2059.1%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15-
DeepSeek-R1-Distill-Qwen-32BDeepSeek, released 2025-01-2062.1%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15-
DeepSeek-R1-Distill-Qwen-7BDeepSeek, released 2025-01-2049.1%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15-
DeepSeek-V3DeepSeek, released 2024-12-2659.1%DeepSeek, DeepSeek-V3-0324 model cardchecked 2026-10-15; printed on 2 more pages-
DeepSeek-V4-Flash-0731DeepSeek89.9%DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pagesEffort: max
DeepSeek-V4-Pro-0813DeepSeek92.4%DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15Effort: max
Qwen3.8-MaxAlibaba, released 2026-08-0392.6%Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14-
Qwen3.7-PlusAlibaba, released 2026-06-0190.3%Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page-
Qwen3.6-27BAlibaba, released 2026-04-2287.8%Alibaba, Qwen3.6-27B model cardchecked 2026-10-15; printed on 1 more page-
Qwen3.6-35B-A3BAlibaba, released 2026-04-1686%Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15; printed on 3 more pages-
Qwen3.6-PlusAlibaba, released 2026-04-0290.4%Z.ai, GLM-5.1 model cardchecked 2026-10-15-
Qwen3.5-122B-A10BAlibaba, released 2026-02-2486.6%Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page-
Qwen3.5-27BAlibaba, released 2026-02-2485.5%Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 2 more pages-
Qwen3.5-35B-A3BAlibaba, released 2026-02-2484.2%Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page-
Qwen3.5-397B-A17BAlibaba, released 2026-02-1688.4%Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page-
Qwen3-235B-A22BAlibaba, released 2025-04-2981.1%Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 2 more pages-
Qwen3-32BAlibaba, released 2025-04-2968.4%DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15-
Qwen3-8BAlibaba, released 2025-04-2962%DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15-
QwQ-32B-PreviewAlibaba, released 2024-11-2754.5%DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15-
Qwen-MaxAlibaba60.1%DeepSeek, DeepSeek-V3-0324 model cardchecked 2026-10-15-
Qwen3-Max-ThinkingAlibaba87.4%Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15-
Qwen3.7-MaxAlibaba92.4%Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page-
Qwen3.8-2.4T-A95BAlibaba93.5%Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19Effort: xhigh
Qwen3.8-27BAlibaba89.2%Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page-
Qwen3.8-Flash-NextAlibaba91.7%Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page-
Kimi K3.1 ProMoonshot AI, released 2026-10-2394.2%Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24Effort: max
Kimi K3Moonshot AI, released 2026-07-1693.5%Moonshot AI, Kimi K3 model cardchecked 2026-10-15; printed on 2 more pagesEffort: max
Kimi K2.6Moonshot AI, released 2026-04-2090.5%Moonshot AI, Kimi K2.6 model cardchecked 2026-10-15; printed on 3 more pages-
Kimi K2.5Moonshot AI, released 2026-01-2787.6%Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15; printed on 5 more pages-
Kimi K2 ThinkingMoonshot AI, released 2025-11-0684.5%Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15; printed on 1 more pageEffort: thinking; Tools: none
Kimi K2 Instruct 0905Moonshot AI, released 2025-09-0574.2%Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15Tools: none
Kimi K2 BaseMoonshot AI, released 2025-07-1148.1%Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15Harness: 5-shot
Kimi K2 InstructMoonshot AI, released 2025-07-1175.1%Moonshot AI, Kimi K2 release pagechecked 2026-10-15-
GLM-5.3-FlashZ.ai, released 2026-08-2691.2%NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19-
GLM-5.3Z.ai, released 2026-08-1888.1%DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages-
GLM-5.2Z.ai, released 2026-06-1691.2%Z.ai, GLM-5.2 model cardchecked 2026-10-15; printed on 3 more pages-
GLM-5.1Z.ai, released 2026-04-0786.2%Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages-
GLM-5Z.ai, released 2026-02-1286%Z.ai, GLM-5 model cardchecked 2026-10-15; printed on 1 more page-
GLM-4.7Z.ai, released 2025-12-2285.7%Z.ai, GLM-4.7 model cardchecked 2026-10-15; printed on 1 more page-
GLM-4.6Z.ai, released 2025-09-3081%Z.ai, GLM-4.7 model cardchecked 2026-10-15-
Mistral Small 4Mistral AI, released 2026-03-1671.2%Mistral AI, Mistral Small 4 model cardchecked 2026-10-15Effort: high
59.1%Mistral AI, Mistral Small 4 model cardchecked 2026-10-15Effort: none
Mistral Large 3Mistral AI, released 2025-12-0264.1%Mistral AI, Mistral Small 4 model cardchecked 2026-10-15-
Mistral Medium 3.1Mistral AI, released 2025-08-1265.7%Mistral AI, Mistral Small 4 model cardchecked 2026-10-15-
Mistral Small 3.2Mistral AI, released 2025-06-2050%Mistral AI, Mistral Small 4 model cardchecked 2026-10-15-
Magistral MediumMistral AI, released 2025-06-1070.8%Mistral AI, Announcing Magistralchecked 2026-10-15-
Mistral Medium 3Mistral AI, released 2025-05-0759.6%Mistral AI, Announcing Magistralchecked 2026-10-15; printed on 1 more page-
MiniMax M3MiniMax, released 2026-06-0192.9%IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15; printed on 1 more page-
MiniMax M2.7MiniMax, released 2026-03-1887%Z.ai, GLM-5.1 model cardchecked 2026-10-15-
MiniMax M2.5MiniMax, released 2026-02-1285.2%MiniMax, MiniMax-M2.5 model cardchecked 2026-10-15-
MiniMax M2.1MiniMax, released 2025-12-2083%MiniMax, MiniMax-M2.5 model cardchecked 2026-10-15-
Nemotron 3.5 Bolt 74B-A9BNVIDIA, released 2026-10-1588.83%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19Model as printed: Nemotron 3.5 Bolt 74B-A9B (BF16)
86.43%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19Model as printed: Nemotron 3.5 Bolt 74B-A9B-24GB (IQ2)
Nemotron 3.5 Super VL 120B-A12BNVIDIA, released 2026-10-1589.52%NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19-
Nemotron 3.5 Lightning 30B-A3BNVIDIA, released 2026-08-1175.57%NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19; printed on 1 more page-
Nemotron 3 UltraNVIDIA, released 2026-06-0487%NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19; printed on 3 more pages-
Nemotron 3 SuperNVIDIA, released 2026-03-1178.6%NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19Tools: none
Nemotron 3 Nano 30B-A3BNVIDIA, released 2025-12-1574.05%NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19Tools: none
MAI-Thinking-1Microsoft, released 2026-08-1284.2%Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19; printed on 1 more page-
Phi-4-reasoning-plusMicrosoft, released 2025-04-3069.3%DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15-
MiMo-V2.5 BaseXiaomi, released 2026-04-2758.1%Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15Harness: 5-shot
MiMo-V2.5-Pro BaseXiaomi, released 2026-04-2766.7%Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15Harness: 5-shot
InklingThinking Machines, released 2026-07-1487.2%Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15; printed on 2 more pagesEffort: 0.99
Inkling-SmallThinking Machines88.6%NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B 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.