{
  "asOf": "2026-07-31",
  "rows": [
    {
      "model": "Claude Opus 5",
      "provider": "Anthropic",
      "apiId": "claude-opus-5",
      "releaseDate": "2026-07-24",
      "category": "frontier",
      "significance": "flagship",
      "openWeight": false,
      "license": "",
      "contextWindow": 1000000,
      "launchInputPerMtok": 5,
      "launchOutputPerMtok": 25,
      "aaIntelligence": 61,
      "oneLiner": "Took the top spot on the Artificial Analysis Intelligence Index at 61, and did it at half the per-token price of Claude Fable 5.",
      "sourceUrl": "https://www.anthropic.com/news/claude-opus-5",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "FLUX 3",
      "provider": "Black Forest Labs",
      "apiId": "",
      "releaseDate": "2026-07-23",
      "category": "image-video",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "oneLiner": "One network spanning image, video, audio and robot action prediction. Video runs in early access; the open-weight Dev build is promised later in 2026.",
      "sourceUrl": "https://www.globenewswire.com/news-release/2026/07/23/3332364/0/en/black-forest-labs-unveils-flux-3-a-new-multimodal-frontier-model-for-visual-intelligence.html",
      "sourceType": "provider-press-release",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Ling-3.0-flash",
      "provider": "Ant Group",
      "apiId": "",
      "releaseDate": "2026-07-23",
      "category": "efficient",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "contextWindow": 256000,
      "oneLiner": "A 124B mixture-of-experts firing only 5.1B parameters per token, which Ant says matches its own 1T flagship. Announced as open weight, but shipped API-only with the weights still unpublished.",
      "sourceUrl": "https://www.businesswire.com/news/home/20260726584441/en/Ant-Group-Unveils-Ling-3.0-Flash-Delivering-Top-Tier-Performance-at-a-Fraction-of-the-Parameter-Scale",
      "sourceType": "provider-press-release",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Gemini 3.6 Flash",
      "provider": "Google",
      "apiId": "",
      "releaseDate": "2026-07-21",
      "category": "efficient",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "contextWindow": 1050000,
      "launchInputPerMtok": 1.5,
      "launchOutputPerMtok": 7.5,
      "oneLiner": "Google's workhorse tier, cut to $7.50 output from the $9.00 that Gemini 3.5 Flash charged, on a claimed 17% drop in output tokens per task.",
      "sourceUrl": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Gemini 3.5 Flash-Lite",
      "provider": "Google",
      "apiId": "",
      "releaseDate": "2026-07-21",
      "category": "efficient",
      "significance": "incremental",
      "openWeight": false,
      "license": "",
      "contextWindow": 1050000,
      "launchInputPerMtok": 0.3,
      "launchOutputPerMtok": 2.5,
      "oneLiner": "The cheapest launch price of any July model at $0.30 in, aimed at classification, extraction and routing rather than reasoning.",
      "sourceUrl": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Gemini 3.5 Flash Cyber",
      "provider": "Google",
      "apiId": "",
      "releaseDate": "2026-07-21",
      "category": "specialist",
      "significance": "incremental",
      "openWeight": false,
      "license": "",
      "oneLiner": "Tuned to find and patch software vulnerabilities, and restricted to governments and trusted partners through the CodeMender pilot.",
      "sourceUrl": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Laguna S 2.1",
      "provider": "poolside",
      "apiId": "",
      "releaseDate": "2026-07-21",
      "category": "open-weight",
      "significance": "notable",
      "openWeight": true,
      "license": "OpenMDW-1.1",
      "contextWindow": 1000000,
      "launchInputPerMtok": 0.1,
      "launchOutputPerMtok": 0.2,
      "oneLiner": "118B total and 8B active, released under OpenMDW-1.1 at $0.10 in and $0.20 out, the cheapest agentic coding model to ship in July.",
      "sourceUrl": "https://poolside.ai/blog/introducing-laguna-s-2-1",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Qwen-Image-3.0",
      "provider": "Alibaba",
      "apiId": "",
      "releaseDate": "2026-07-21",
      "category": "image-video",
      "significance": "incremental",
      "openWeight": false,
      "license": "",
      "oneLiner": "Closed and invite-only at launch, with no model card, weights or published benchmarks to check the multi-panel layout claims against.",
      "sourceUrl": "https://www.digitalapplied.com/blog/seven-days-seven-releases-july-2026-model-wave",
      "sourceType": "secondary",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Qwen-Audio-3.0-TTS Plus",
      "provider": "Alibaba",
      "apiId": "",
      "releaseDate": "2026-07-20",
      "category": "speech",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "oneLiner": "Took first place on the Artificial Analysis text-to-speech arena. Billed per character, not per token, at roughly a third of what ElevenLabs charges.",
      "sourceUrl": "https://www.marktechpost.com/2026/07/20/alibabas-tongyi-lab-releases-qwen-audio-3-0-tts-a-hosted-text-to-speech-model-in-flash-and-plus-tiers-across-16-languages/",
      "sourceType": "secondary",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Qwen-Audio-3.0-TTS Flash",
      "provider": "Alibaba",
      "apiId": "",
      "releaseDate": "2026-07-20",
      "category": "speech",
      "significance": "incremental",
      "openWeight": false,
      "license": "",
      "oneLiner": "The real-time tier of the same text-to-speech release, covering 16 languages and 20 Chinese dialect regions, hosted only on Alibaba Cloud Model Studio.",
      "sourceUrl": "https://www.marktechpost.com/2026/07/20/alibabas-tongyi-lab-releases-qwen-audio-3-0-tts-a-hosted-text-to-speech-model-in-flash-and-plus-tiers-across-16-languages/",
      "sourceType": "secondary",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Qwen3.8-Max-Preview",
      "provider": "Alibaba",
      "apiId": "",
      "releaseDate": "2026-07-19",
      "category": "frontier",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "contextWindow": 1000000,
      "oneLiner": "A 2.4T-parameter preview shown at the World AI Conference with no model card, no license and no independent benchmarks published alongside it.",
      "sourceUrl": "https://www.marktechpost.com/2026/07/19/alibaba-previews-qwen3-8-max-a-2-4-trillion-parameter-multimodal-model-days-after-moonshots-kimi-k3-open-weight-launch/",
      "sourceType": "secondary",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Kimi K3",
      "provider": "Moonshot",
      "apiId": "kimi-k3",
      "releaseDate": "2026-07-16",
      "category": "frontier",
      "significance": "flagship",
      "openWeight": true,
      "license": "",
      "contextWindow": 1050000,
      "launchInputPerMtok": 3,
      "launchOutputPerMtok": 15,
      "aaIntelligence": 57,
      "oneLiner": "2.8T parameters and the highest-scoring open-weight model of the month. Weights followed on July 26, a day inside Moonshot's own deadline.",
      "sourceUrl": "https://platform.kimi.ai/docs/pricing/chat-k3",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Inkling",
      "provider": "Thinking Machines",
      "apiId": "thinkingmachines/Inkling",
      "releaseDate": "2026-07-15",
      "category": "open-weight",
      "significance": "notable",
      "openWeight": true,
      "license": "Apache 2.0",
      "contextWindow": 1000000,
      "launchInputPerMtok": 1.87,
      "launchOutputPerMtok": 4.68,
      "aaIntelligence": 41,
      "oneLiner": "975B total and 41B active under Apache 2.0, the most permissive license anyone has attached to a model at that parameter scale.",
      "sourceUrl": "https://tinker-docs.thinkingmachines.ai/tinker/models/",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "GPT-5.6 Sol",
      "provider": "OpenAI",
      "apiId": "",
      "releaseDate": "2026-07-09",
      "category": "frontier",
      "significance": "flagship",
      "openWeight": false,
      "license": "",
      "contextWindow": 1050000,
      "launchInputPerMtok": 5,
      "launchOutputPerMtok": 30,
      "aaIntelligence": 59,
      "oneLiner": "The reasoning tier of the GPT-5.6 line and the most expensive output token of any July release at $30 per million.",
      "sourceUrl": "https://developers.openai.com/api/docs/pricing",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "GPT-5.6 Terra",
      "provider": "OpenAI",
      "apiId": "",
      "releaseDate": "2026-07-09",
      "category": "frontier",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "contextWindow": 1050000,
      "launchInputPerMtok": 2.5,
      "launchOutputPerMtok": 15,
      "aaIntelligence": 55,
      "oneLiner": "The middle tier, launched at half of Sol while scoring within four points of it on the Artificial Analysis Intelligence Index. Cut 20% on July 30, 2026 to $2/$12, which is now 40% of Sol.",
      "sourceUrl": "https://developers.openai.com/api/docs/pricing",
      "sourceType": "provider",
      "verifiedDate": "2026-07-31"
    },
    {
      "model": "GPT-5.6 Luna",
      "provider": "OpenAI",
      "apiId": "",
      "releaseDate": "2026-07-09",
      "category": "efficient",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "contextWindow": 1050000,
      "launchInputPerMtok": 1,
      "launchOutputPerMtok": 6,
      "aaIntelligence": 51,
      "oneLiner": "The high-volume tier, launched at $1 in and $6 out, the best intelligence-per-dollar OpenAI shipped in July. Cut 80% on July 30 to $0.20/$1.20, under the retired GPT-5.4 nano floor.",
      "sourceUrl": "https://developers.openai.com/api/docs/pricing",
      "sourceType": "provider",
      "verifiedDate": "2026-07-31"
    },
    {
      "model": "Muse Spark 1.1",
      "provider": "Meta",
      "apiId": "muse-spark-1.1",
      "releaseDate": "2026-07-09",
      "category": "multimodal",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "contextWindow": 1000000,
      "oneLiner": "Meta Superintelligence Labs shipped its first paid model, breaking the open-weight-only posture Meta had held since Llama.",
      "sourceUrl": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Grok 4.5",
      "provider": "xAI",
      "apiId": "",
      "releaseDate": "2026-07-08",
      "category": "frontier",
      "significance": "flagship",
      "openWeight": false,
      "license": "",
      "contextWindow": 500000,
      "launchInputPerMtok": 2,
      "launchOutputPerMtok": 6,
      "aaIntelligence": 54,
      "oneLiner": "Trained on real Cursor session data and priced at $2 in and $6 out, well under half of what Opus 4.8 and GPT-5.5 charged at the time.",
      "sourceUrl": "https://x.ai/news/grok-4-5",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "SWE-1.7",
      "provider": "Cognition",
      "apiId": "",
      "releaseDate": "2026-07-08",
      "category": "specialist",
      "significance": "notable",
      "openWeight": false,
      "license": "",
      "oneLiner": "Post-trained on top of Moonshot's already RL-heavy Kimi K2.7 Code, and served inside Devin only. Not sold as a standalone API.",
      "sourceUrl": "https://cognition.com/blog/swe-1-7",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    },
    {
      "model": "Cohere Transcribe Arabic",
      "provider": "Cohere",
      "apiId": "",
      "releaseDate": "2026-07-07",
      "category": "speech",
      "significance": "incremental",
      "openWeight": true,
      "license": "Apache 2.0",
      "oneLiner": "A 2B open-weight speech recognition model built for Arabic dialect variation and Arabic-English code-switching.",
      "sourceUrl": "https://cohere.com/blog/transcribe-arabic",
      "sourceType": "provider",
      "verifiedDate": "2026-07-29"
    }
  ]
}