Frontier language model releases and evaluations, filtered for signal from the Artificial Analysis changelog. https://crustylabs.ai/frontier.html Sun, 25 Oct 2026 13:30:06 +0000 360 https://artificialanalysis.ai/models/kimi-k3-1-pro fc5b7e1170a6f912bfe2f161efb8b08a Model evaluation Fri, 23 Oct 2026 12:00:00 +0000 Kimi K3.1 Pro — Intelligence Index 55 https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks 8bb8a4035f6d1c1f33a16918a77a42ae Article Fri, 23 Oct 2026 12:00:00 +0000 Kimi K3.1 Pro launches at 4th on the Intelligence Index and will lead open weights models https://artificialanalysis.ai/articles/healthbench-professional-health-conversations 126109cb94c3b5fcc4eeaa83362ff396 Article Mon, 19 Oct 2026 12:00:00 +0000 HealthBench and HealthBench Professional: Evaluating models in realistic health conversations https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017 14b2108b18559a7bec3fb19057fbeda6 Model evaluation Sun, 18 Oct 2026 12:00:00 +0000 DeepSeek V4.1 Flash 1017 (Max) — Intelligence Index 45 https://artificialanalysis.ai/articles/reflection-beam 0b49b85ff792e2ee21c20fb520792f15 Article Fri, 16 Oct 2026 12:00:00 +0000 Reflection has released Beam, their first model launch https://artificialanalysis.ai/articles/nemotron-3-5-super-and-bolt 754578fb3d391813affa121a1504aca9 Article Thu, 15 Oct 2026 12:00:00 +0000 NVIDIA Releases Nemotron 3.5 Super VL and Nemotron 3.5 Bolt 74B A9B https://artificialanalysis.ai/articles/aa-robotics 23c3bd570081cdfeaece093f3c782c13 Article Wed, 14 Oct 2026 12:00:00 +0000 Welcome to the era of embodied AI: Introducing AA-Robotics v0.1 https://artificialanalysis.ai/articles/artificial-analysis-decision-index 78eb5bde028274c88450b4d8d8ba7d2c Article Tue, 13 Oct 2026 12:00:00 +0000 Artificial Analysis Decision Index v1.0 https://artificialanalysis.ai/articles/aa-3d 19540d364df2e51a812bd884c10ac1d0 Article Mon, 12 Oct 2026 12:00:00 +0000 Announcing AA-3D: a benchmark for AI models building interactive 3D experiences https://artificialanalysis.ai/articles/frontiercode 19d4bcb3020a9e6d146308d33b467af2 Article Mon, 12 Oct 2026 12:00:00 +0000 Announcing FrontierCode on Artificial Analysis: can AI models write code maintainers would merge? https://artificialanalysis.ai/models/muse-wonder 42b26bf5e91f9d01761ec89650e46c01 Model evaluation Mon, 12 Oct 2026 12:00:00 +0000 Muse Wonder (Max) — Intelligence Index 52 https://artificialanalysis.ai/articles/muse-wonder 0f96ef481c552348aa73634a725ae889 Article Mon, 12 Oct 2026 12:00:00 +0000 Muse Wonder and Muse Wonder Full: a material jump in intelligence over previous Meta models https://artificialanalysis.ai/models/muse-wonder-full 1b04bb8984e48e0bdd32be96940661bf Model evaluation Mon, 12 Oct 2026 12:00:00 +0000 Muse Wonder Full (Max) — Intelligence Index 56 https://artificialanalysis.ai/articles/harvey-lab-aa-v1-1 11b0543c55b12477f94ab6d21cff055b Article Thu, 08 Oct 2026 12:00:00 +0000 Announcing Harvey LAB-AA v1.1: adding hallucination checks to raise the bar for agentic legal work https://artificialanalysis.ai/articles/trusted-access-models-cyber-index 1f432f5c605a3a60e3b1174623c7cc9b Article Thu, 08 Oct 2026 12:00:00 +0000 Introducing trusted-access models to the Artificial Analysis Cyber Index https://artificialanalysis.ai/articles/claude-haiku-5-5 e2ae522931d52e9c1071ebce9ab29662 Article Wed, 07 Oct 2026 12:00:00 +0000 Anthropic has released Claude Haiku 5.5 https://artificialanalysis.ai/articles/mistral-large-4-france-ai 0b18e2a6d5e761a84582eac327f57967 Article Tue, 06 Oct 2026 12:00:00 +0000 Mistral has released Mistral Large 4, making France home to the most intelligent model outside the US and China https://artificialanalysis.ai/articles/aa-agentperf-local 6b783c7d78f20a4d8c05d24bc4e41986 Article Thu, 01 Oct 2026 12:00:00 +0000 AA-AgentPerf-Local: Benchmarking local AI agents on laptops and workstations https://artificialanalysis.ai/articles/artificial-analysis-capability-indices-v1-1 bb24b390d1479e39cde6d5acf3607a65 Article Thu, 01 Oct 2026 12:00:00 +0000 Announcing Artificial Analysis Capability Indices v1.1 https://artificialanalysis.ai/articles/artificial-analysis-intelligence-index-v4-2 1e224d0a2c1b220d067bef77ee237beb Article Thu, 01 Oct 2026 12:00:00 +0000 Announcing Artificial Analysis Intelligence Index v4.2 https://artificialanalysis.ai/articles/artificial-analysis-cyber-index 6b0e546e4163dfb04e081b3bb59c4e5e Article Thu, 01 Oct 2026 12:00:00 +0000 Announcing the Artificial Analysis Cyber Index Alliance https://artificialanalysis.ai/articles/artificial-analysis-intelligence-index-v4-3 6d30d7075ba0ec932d4a6fcf6af4a131 Article Thu, 01 Oct 2026 12:00:00 +0000 Announcing the Artificial Analysis Intelligence Index v4.3 https://artificialanalysis.ai/articles/ant-group-releases-finance-focused-ling-3-0-flash-fin 85092c2640382f4d6b8bdb44695b5d59 Article Thu, 01 Oct 2026 12:00:00 +0000 Ant Group releases finance-focused Ling-3.0-flash-Fin https://artificialanalysis.ai/articles/benchmarking-gpt-6-astra 9d52185f132fea7028053dac5fd7620b Article Thu, 01 Oct 2026 12:00:00 +0000 Benchmarking GPT-6 Astra https://artificialanalysis.ai/articles/benchmarking-grok-4-7 c0e78c550bf8beeebe6a5542d19498a7 Article Thu, 01 Oct 2026 12:00:00 +0000 Benchmarking Grok 4.7 https://artificialanalysis.ai/models/claude-fable-5-1-high 6265fdaee012dca6434b3e2f8af81b9d Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) — Intelligence Index 51 https://artificialanalysis.ai/models/claude-fable-5-1-low 2296e44a064036819b175b0cfd991836 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) — Intelligence Index 47 https://artificialanalysis.ai/models/claude-fable-5-1 35dadd99917f6009850030d61bc00f71 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) — Intelligence Index 53 https://artificialanalysis.ai/models/claude-fable-5-1-medium 1d09eb118509ef0b8ec54405843e3c43 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) — Intelligence Index 49 https://artificialanalysis.ai/models/claude-fable-5-1-xhigh 77a3847f7ca1c0e2dd0f7bf9e80c77d9 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) — Intelligence Index 53 https://artificialanalysis.ai/models/claude-fable-5-1-high 696b85586982ee05c4fc28bb51c0bcd7 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (High, Default Fallback) — Intelligence Index 51 https://artificialanalysis.ai/models/claude-fable-5-1-low 1e9c946aec0dfa835560c76930f0412b Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Low, Default Fallback) — Intelligence Index 47 https://artificialanalysis.ai/models/claude-fable-5-1 af788fcb6a66f2834b816cda5321e785 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Max, Default Fallback) — Intelligence Index 53 https://artificialanalysis.ai/models/claude-fable-5-1-medium 2e02e01ac45d65301027b6caf41f3e82 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Medium, Default Fallback) — Intelligence Index 49 https://artificialanalysis.ai/models/claude-fable-5-1-xhigh 212da73b4fb29dab72fc566fbbe60000 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 (Xhigh, Default Fallback) — Intelligence Index 53 https://artificialanalysis.ai/articles/claude-fable-5-1 a8c321de9a0f7f17f2795907be719e3c Article Thu, 01 Oct 2026 12:00:00 +0000 Claude Fable 5.1 tops the Artificial Analysis Intelligence Index https://artificialanalysis.ai/models/claude-opus-5-5-high 018fe635d0dd714c02f13715b00acf5f Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback) — Intelligence Index 54 https://artificialanalysis.ai/models/claude-opus-5-5 a29e198f45f1c636b5b07b9105fb3194 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) — Intelligence Index 58 https://artificialanalysis.ai/models/claude-opus-5-5-medium ba142312ecbc1f56085b7432996996cb Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback) — Intelligence Index 51 https://artificialanalysis.ai/models/claude-opus-5-5-xhigh f211c85b0d6065e871382897524a98ff Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback) — Intelligence Index 56 https://artificialanalysis.ai/models/claude-opus-5-5-high 5b56d2ab33ce5972ba4b5ea6a34a1ef7 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (High, Default Fallback) — Intelligence Index 54 https://artificialanalysis.ai/models/claude-opus-5-5 cf35fc44e7d72ac886c17af0bfd8f3f8 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (Max, Default Fallback) — Intelligence Index 58 https://artificialanalysis.ai/models/claude-opus-5-5-medium a87eea9ecb0e5c6438024ddabeb58cdb Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (Medium, Default Fallback) — Intelligence Index 51 https://artificialanalysis.ai/models/claude-opus-5-5-xhigh fb4f910d5bcc9759148bec4e078dfcb6 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 (Xhigh, Default Fallback) — Intelligence Index 56 https://artificialanalysis.ai/articles/claude-opus-5-5 c028eb0360367ae3d16fa8c58e467940 Article Thu, 01 Oct 2026 12:00:00 +0000 Claude Opus 5.5 takes the top spot on the Artificial Analysis Intelligence Index https://artificialanalysis.ai/models/claude-sonnet-5-5-high 58e814a4279dd8196f989a18c318a003 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback) — Intelligence Index 47 https://artificialanalysis.ai/models/claude-sonnet-5-5 1259500dfddeddfd5168deb1c9267739 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) — Intelligence Index 56 https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh 75e261960d50563e18ee27d0bf3a88da Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback) — Intelligence Index 52 https://artificialanalysis.ai/models/claude-sonnet-5-5-high aadaa94ca985cfae70f40a2728cd187c Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Sonnet 5.5 (High, Default Fallback) — Intelligence Index 47 https://artificialanalysis.ai/models/claude-sonnet-5-5 27ae7213e7acfcdec81f19dca6fc14c2 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Sonnet 5.5 (Max, Default Fallback) — Intelligence Index 56 https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh bee019fd7a18d0d254ae4a35128fa287 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Claude Sonnet 5.5 (Xhigh, Default Fallback) — Intelligence Index 52 https://artificialanalysis.ai/articles/claude-sonnet-5-5 8c53d3b822cf155ff1abc7d7a4c155da Article Thu, 01 Oct 2026 12:00:00 +0000 Claude Sonnet 5.5 reaches #2 on the Artificial Analysis Intelligence Index https://artificialanalysis.ai/models/gemini-4-argon 81e408f4314ebc061bb58bf67e273df7 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Gemini 4 Argon (High) — Intelligence Index 53 https://artificialanalysis.ai/articles/gemini-4-argon-google-top-three-labs 8de5891387d21a29a57b047f8cd69997 Article Thu, 01 Oct 2026 12:00:00 +0000 Gemini 4 Argon: Google is back as one of the top three labs in intelligence achieved https://artificialanalysis.ai/articles/gemini-3-8-flash a676e7d3f0591064d09784f02788592b Article Thu, 01 Oct 2026 12:00:00 +0000 Google has released Gemini 3.8 Flash, its fourth Flash model in under four months https://artificialanalysis.ai/models/gpt-6-astra-high 87aaf1dd1f00c89bf5b966705032b5de Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6 Astra (High) — Intelligence Index 51 https://artificialanalysis.ai/models/gpt-6-astra-low 91c8dc075b79a89ff72c7499d1d82f48 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6 Astra (Low) — Intelligence Index 46 https://artificialanalysis.ai/models/gpt-6-astra 8b43be289f65de30c9552f1b58513e53 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6 Astra (Max) — Intelligence Index 53 https://artificialanalysis.ai/models/gpt-6-astra-medium 2c1f8eb9e24fa53135bbad79f87e77cc Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6 Astra (Medium) — Intelligence Index 50 https://artificialanalysis.ai/models/gpt-6-astra-xhigh 293fd14c263b64442b4d9d9e64087fad Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6 Astra (Xhigh) — Intelligence Index 52 https://artificialanalysis.ai/models/gpt-6-sol 3a353c39d14dd98be5d881d4257d9b99 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6 Sol (Max) — Intelligence Index 48 https://artificialanalysis.ai/articles/gpt-6-sol-and-luna-push-the-cost-efficiency-frontier e0a103741930e64e06689abcf21df375 Article Thu, 01 Oct 2026 12:00:00 +0000 GPT-6 Sol and Luna push the cost efficiency frontier https://artificialanalysis.ai/models/gpt-6-1-sol-high e0239b85fcc30c89b5d07c05f96cd5fa Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6.1 Sol (High) — Intelligence Index 50 https://artificialanalysis.ai/models/gpt-6-1-sol 783872735b69b1785a703b0e4ddf1c75 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6.1 Sol (Max) — Intelligence Index 52 https://artificialanalysis.ai/models/gpt-6-1-sol-medium 62f61f5a3f3343f4b0e4a13acbeecfd3 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6.1 Sol (Medium) — Intelligence Index 48 https://artificialanalysis.ai/models/gpt-6-1-sol-xhigh 3a40e669492810f241bbba0616821ca8 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 GPT-6.1 Sol (Xhigh) — Intelligence Index 51 https://artificialanalysis.ai/articles/gpt-6-1-sol-replaces-gpt-6-sol-after-just-7-days-with-near-astra-intelligence 0909302bd40804e704f23baadfcc0f37 Article Thu, 01 Oct 2026 12:00:00 +0000 GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence https://artificialanalysis.ai/models/grok-4-7-high 98c8e3cd4d93338ad28a4f558f2905a7 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Grok 4.7 (High) — Intelligence Index 46 https://artificialanalysis.ai/models/grok-4-7 c57e166478eee3c97d85e41b96fdb322 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Grok 4.7 (Xhigh) — Intelligence Index 46 https://artificialanalysis.ai/articles/korean-ai-lab-upstage-releases-solar-mini-4 17984978170112454dff2c9544f4175d Article Thu, 01 Oct 2026 12:00:00 +0000 Korean AI Lab Upstage releases Solar Mini 4 https://artificialanalysis.ai/models/mimo-v2-6-pro f85bf3f003ce482b63bd7a9ab8138aa6 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 MiMo-V2.6-Pro — Intelligence Index 46 https://artificialanalysis.ai/models/muse-spark-1-3 81d1829cdc7292580b7cd241b7cf74ad Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Muse Spark 1.3 (Max) — Intelligence Index 48 https://artificialanalysis.ai/models/muse-spark-1-3-xhigh 271e716e2290c4cc7f7d191710745220 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Muse Spark 1.3 (Xhigh) — Intelligence Index 45 https://artificialanalysis.ai/articles/muse-spark-1-3 b63a03ef88710050cbc1142f5743a961 Article Thu, 01 Oct 2026 12:00:00 +0000 Muse Spark 1.3: Meta reaches the frontier https://artificialanalysis.ai/articles/openbmb-releases-minicpm5-2b d195d5acfe55ca9392c39bc0a0273e32 Article Thu, 01 Oct 2026 12:00:00 +0000 OpenBMB releases MiniCPM5-2B https://artificialanalysis.ai/models/qwen3-8-max 450ad9de1ba0d2267aeb57a178ba58e3 Model evaluation Thu, 01 Oct 2026 12:00:00 +0000 Qwen3.8 Max (0902) — Intelligence Index 45 https://artificialanalysis.ai/articles/agnes-ai-releases-agnes-2-5-pro-beta 5f3c285f17eeee420b3f73a32a616a64 Article Thu, 27 Aug 2026 12:00:00 +0000 Agnes AI releases Agnes 2.5 Pro Beta https://artificialanalysis.ai/models/qwen3-8-flash-next 5c5fb05a002a631b91a14d70036c166b Model evaluation Thu, 27 Aug 2026 12:00:00 +0000 Qwen3.8-Flash-Next — Intelligence Index 56 https://artificialanalysis.ai/models/agnes-2-5-pro-beta 35e015b42c6692c0173a7b5ca2e3e994 Model evaluation Wed, 26 Aug 2026 12:00:00 +0000 Agnes 2.5 Pro Beta — Intelligence Index 49 https://artificialanalysis.ai/models/glm-5-3-flash 9a08f3982636b29add7b50334af1a2e3 Model evaluation Wed, 26 Aug 2026 12:00:00 +0000 GLM-5.3-Flash — Intelligence Index 57