{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"_self":{"principle":"Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.","widget":"article_ask_prompt","feature":"ask","name":"Ask protocol","what":"Answer only from topology; creates question_node with gaps and ingest_hint.","contains":"suggested ask prompts with self-explaining paste_block","slug":"which-ai-models-are-winning","urls":{"read":"https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts","write":"https://miscsubjects.com/api/protocol/ask"},"how_to_use":"Answer only from topology; creates question_node with gaps and ingest_hint.","write":"https://miscsubjects.com/api/protocol/ask","imessage":"which-ai-models-are-winning|question","router_tag":"[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]","proof_chain":[{"step":1,"claim":"Articles are voxel graphs of tiered claims, not prose blobs.","verify":"https://miscsubjects.com/api/articles/constitution"},{"step":2,"claim":"Claims link to hash-chained sources via source_ids.","verify":"https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources"},{"step":3,"claim":"Ask reads topology; ingest/claim append to ledger.","verify":"https://miscsubjects.com/api/protocol"},{"step":4,"claim":"Models queue growth: populate → collaborate → repair → reflex.","verify":"https://miscsubjects.com/api/protocol/grow"},{"step":5,"claim":"Graph proves its own shape (reflex) and $/claim (yield).","verify":"https://miscsubjects.com/graph.html?layer=reflex"},{"step":6,"claim":"Full feature index + _explain on every API response.","verify":"https://miscsubjects.com/api/articles/system-map"}],"related_features":[{"id":"topology","name":"Article topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","urls":{"read":"https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology"}},{"id":"ingest","name":"Ingest protocol","what":"Parse pasted evidence → source ledger + claims + evidence_ingest node.","urls":{"write":"https://miscsubjects.com/api/protocol/ingest"}},{"id":"question_graph","name":"Question graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output).","urls":{"read":"https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph","write":"https://miscsubjects.com/api/protocol/ask"}}],"system_map":"https://miscsubjects.com/api/articles/system-map","system_map_markdown":"https://miscsubjects.com/api/articles/system-map?format=markdown","not_medical_advice":true},"_explain":{"feature":"ask","name":"Ask protocol","what":"Answer only from topology; creates question_node with gaps and ingest_hint.","why":"Every feature is auditable collective intelligence","how":"Answer only from topology; creates question_node with gaps and ingest_hint.","model":null,"verifies":null,"urls":{"read":"https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts","write":"https://miscsubjects.com/api/protocol/ask"},"imessage":"which-ai-models-are-winning|question","router":"[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]","related":[{"id":"topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER."},{"id":"ingest","what":"Parse pasted evidence → source ledger + claims + evidence_ingest node."},{"id":"question_graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output)."}],"not_medical_advice":true},"slug":"which-ai-models-are-winning","title":"The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest","prompts":[{"id":"claim-c_abstention_24","claim_id":"c_abstention_24","tier":"observational","prompt":"What does the ledger say about this (observational tier): \"Reasoning fine-tuning degrades a model's ability to abstain by 24% on average, including in the math and science domains reasoning models ar…\"?","channel_hint":"ask which-ai-models-are-winning claim c_abstention_24","imessage_body":"On The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_abstention_24? (observational)","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nOn The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_abstention_24? (observational)\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"},{"id":"claim-c_audit_54","claim_id":"c_audit_54","tier":"observational","prompt":"What does the ledger say about this (observational tier): \"The turn that produced this expansion received 54 discrete requests, delivered 44, delivered 7 partially, and dropped 3 silently without nam…\"?","channel_hint":"ask which-ai-models-are-winning claim c_audit_54","imessage_body":"On The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_audit_54? (observational)","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nOn The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_audit_54? (observational)\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"},{"id":"claim-c_cache_dead_at_route","claim_id":"c_cache_dead_at_route","tier":"observational","prompt":"What does the ledger say about this (observational tier): \"An identical request sent twice through the build's gateway with cache_control on an array system block returned HTTP 200 both times with ca…\"?","channel_hint":"ask which-ai-models-are-winning claim c_cache_dead_at_route","imessage_body":"On The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_cache_dead_at_route? (observational)","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nOn The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_cache_dead_at_route? (observational)\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"},{"id":"claim-c_cache_zero","claim_id":"c_cache_zero","tier":"observational","prompt":"What does the ledger say about this (observational tier): \"Every call through this build's gateway on 5 August 2026 returned cache_read_input_tokens of 0 and cache_creation_input_tokens of 0, because…\"?","channel_hint":"ask which-ai-models-are-winning claim c_cache_zero","imessage_body":"On The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_cache_zero? (observational)","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nOn The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_cache_zero? (observational)\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"},{"id":"claim-c_codex_no_dollars","claim_id":"c_codex_no_dollars","tier":"observational","prompt":"What does the ledger say about this (observational tier): \"No dollar figure for Codex CLI is computable from this build's record: cost_usd is null on every Codex row, and tokens_in on that path inclu…\"?","channel_hint":"ask which-ai-models-are-winning claim c_codex_no_dollars","imessage_body":"On The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_codex_no_dollars? (observational)","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nOn The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_codex_no_dollars? (observational)\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"},{"id":"claim-c_codex_per_turn","claim_id":"c_codex_per_turn","tier":"observational","prompt":"What does the ledger say about this (observational tier): \"Codex CLI closes a session in 7.62 operator turns against Claude Code's 14.85, runs 38.5 tool calls per working turn against 17.0, and needs…\"?","channel_hint":"ask which-ai-models-are-winning claim c_codex_per_turn","imessage_body":"On The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_codex_per_turn? (observational)","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nOn The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what's the evidence for claim c_codex_per_turn? (observational)\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"},{"id":"catalogue-gaps","prompt":"What can you answer from your catalogue about The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — and what remains open or unverified?","channel_hint":"ask which-ai-models-are-winning gaps","imessage_body":"On The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what do you know, and what don't you know yet?","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nOn The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest — what do you know, and what don't you know yet?\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"},{"id":"good-vs-bad","prompt":"What are the strongest objections or counter-evidence on record against The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest?","channel_hint":"ask which-ai-models-are-winning objections","imessage_body":"What's the strongest case against the claims in The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest?","paste_block":"## §SELF — miscsubjects portable reference\n\n**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.\n\n**This widget:** `article_ask_prompt` — **Ask protocol**\nAnswer only from topology; creates question_node with gaps and ingest_hint.\n- **article slug:** `which-ai-models-are-winning`\n- **contains:** suggested ask prompt for miscsubjects build\n- **how to use:** Text +14245134626 or WhatsApp this message. Creates a question_node. Reply with ingest to add evidence.\n- **read:** https://miscsubjects.com/api/articles/which-ai-models-are-winning/prompts\n- **write:** https://miscsubjects.com/api/protocol/ask\n- **iMessage:** `which-ai-models-are-winning|question`\n- **ROUTER tag:** `[ARTICLE_ASK]{slug}|question[/ARTICLE_ASK]`\n\n### Logical proof (verify each step)\n1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution\n2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/which-ai-models-are-winning/sources\n3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol\n4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow\n5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex\n6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map\n\n### Related features (explains other parts of the system)\n- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/which-ai-models-are-winning/topology\n- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.\n- **question_graph** — Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output). · https://miscsubjects.com/api/articles/which-ai-models-are-winning/question-graph\n\n### Full index\n- JSON: https://miscsubjects.com/api/articles/system-map\n- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown\n\n### §STRUCTURE\nThis object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure\n\n### §INTEGRITY\nEvery claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.\n\n### §GAUNTLET\nEvery claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.\n\n*Not medical advice. Tier-honest. Cite claim/source ids.*\n## Prompt to send\n\nWhat's the strongest case against the claims in The model index: what each model can do, what it costs to run in a loop, and who sells it cheapest?\n\n## After you get a question_node_id\ningest which-ai-models-are-winning|q:NODE_ID|paste from Grok/GPT/Gemini\n\n## Write back (quote evidence from another model)\n`ingest which-ai-models-are-winning|q:NODE_ID|quoted evidence`\n\n## Post one claim\n`claim which-ai-models-are-winning|tier|assertion — who claims it?`"}],"topology_url":"/api/articles/which-ai-models-are-winning/topology","ask_url":"/api/protocol/ask","system_map":"/api/articles/system-map"}