Skip to content
AI Atlas
Families

Model families

Families group canonical releases (Llama 3.1, Qwen3, Claude…). Counts, releases and parameter ranges are aggregated from the members' sourced claims; benchmark ranks are the best rank of any member in the benchmark's primary group.

197 families

Reset

1 row on this page are label-based families (not yet canonical entities)canonical: true = model_family entity; false = legacy attributes.family label awaiting canonicalisation. benchmark_best = best rank of any member in each benchmark's primary group.

Model families
FamilyOrganizationModelsFirst · latest releaseParametersModalitiesLicencesBest benchmark ranks
GPT 4.0125OpenAI1 · no results
GPT 4.32OpenAI1 · no results
GPT 4.5OpenAI1 · Aider polyglot — well-formed responses #27Aider polyglot #34AA Intelligence Index #243
Gemini 3.6Google121 Jul 2026 · 21 Jul 2026audiodocumentimagetextvideoMMMU-Pro #7LiveBench Instruction Following #9LiveBench Language #13
Gemini 3.7Google113 Aug 2026 · 13 Aug 2026audiodocumentimagetextvideoLiveBench Instruction Following #2MMMU-Pro #3SciCode #3
Gemini 3.8Google12 Sept 2026 · 2 Sept 2026audiodocumentimagetextvideoLiveBench Instruction Following #1GPQA Diamond #2MMMU-Pro #2
Gemma 2Google113 Jul 2024 · 13 Jul 2024textno results
Gemma3Tencent14 Nov 2025 · 4 Nov 202511.8BOther 1no results
Granite 3.3IBM1 · Terminal-Bench #279τ²-bench #293IFBench #316
Grok 2xAI122 Aug 2025 · 22 Aug 2025GPQA Diamond #326AA Intelligence Index #336Humanity's Last Exam #444
Grok 4.1SpaceXAI1 · τ²-bench #38GPQA Diamond #95MMMU-Pro #98
Grok 4.3xAI130 Apr 2026 · 30 Apr 2026imagetextIFBench #1τ²-bench #9MMMU-Pro #30
Grok 4.5xAI18 Jul 2026 · 8 Jul 2026imagetextGPQA Diamond #13MMMU-Pro #16SciCode #16
Grok 4.6xAI112 Aug 2026 · 12 Aug 2026imagetextGPQA Diamond #3LiveBench Reasoning #7AA Intelligence Index #8
Imagen 4Google1 · no results
InternLM3InternLM (Shanghai AI Laboratory)113 Jan 2025 · 13 Jan 20258.8BApache-2.0 1no results
LFMLiquid AI1 · Humanity's Last Exam #318GPQA Diamond #406AA Intelligence Index #424
LFM2.1Liquid AI110 Jul 2025 · 10 Jul 20251.17BOther 1Terminal-Bench #279τ²-bench #282Humanity's Last Exam #283
LFM2.2Liquid AI1 · Terminal-Bench #265τ²-bench #277Humanity's Last Exam #287
LlamaMeta AI130 Apr 2025 · 30 Apr 2025imagetextno results
Llama 3.3Meta AI126 Nov 2024 · 26 Nov 202470.5BtextLlama-3.3-Community 1no results
Llama 3.3Sao10K118 Dec 2024 · 18 Dec 2024textno results
MiniMax 01MiniMax112 Jan 2025 · 12 Jan 2025456.1Bimagetextno results
MolmoAllen Institute for AI1 · MMMU-Pro #156Terminal-Bench #279τ²-bench #302
Nova 2Amazon Web Services12 Dec 2025 · 2 Dec 2025documentimagetextvideono results
OLMoAllen Institute for AI112 Apr 2024 · 12 Apr 20241.18BApache-2.0 1no results
OLMo 3.1Allen Institute for AI1 · IFBench #87τ²-bench #242Humanity's Last Exam #264
OLMo 3.1025Allen Institute for AI112 Sept 2025 · 12 Sept 20257.3BApache-2.0 1no results
PaLM 2Google1 · AA Intelligence Index #426
ParselabelCohere1 · no results
Phi2Microsoft113 Dec 2023 · 13 Dec 20232.78BMIT 1no results
Phi3Microsoft1 · Terminal-Bench #279τ²-bench #302IFBench #309
Phi3.5Microsoft116 Aug 2024 · 16 Aug 20244.15BMIT 1no results
Qwen1.5Alibaba Group1 · AA Intelligence Index #406GPQA Diamond #430
Qwen3.1Alibaba Group1 · τ²-bench #217Terminal-Bench #279IFBench #293
Seed 2.1ByteDance112 Aug 2026 · 12 Aug 2026imagetextvideono results
Step3StepFun1 · MMMU-Pro #96IFBench #148Humanity's Last Exam #190
Step3.7StepFun128 May 2026 · 28 May 2026imagetextvideoτ²-bench #4MMMU-Pro #44Terminal-Bench #54
TitanAmazon Web Services130 Apr 2024 · 30 Apr 2024Other 1no results
Claude 2.00 · no results
Claude 4.10 · no results
Llama0 · no results
Llama 3.10 · no results
Llama 3.10 · no results
Mistral0 · no results
Qwen30 · no results
Seed0 · no results

Family canonical: true = model_family entity; false = legacy attributes.family label awaiting canonicalisation. benchmark_best = best rank of any member in each benchmark's primary group.