Claude Mythos 5.2 vs Glimpse

Claude Mythos 5.2 95

Model reading for claude-mythos-5-2 on the Claude API. Platform facts are the Claude API listing's (anthropic-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Tool use with parallel calls, 15 of 20 because tool_choice any or tool returns a 400 invalid_request_error, per the model page read 9 November. Structured outputs (15). Prompt caching with reads at $0.20, 0.025x input, per the pricing page read 9 November (15). 1M context by default and at most, 128K output (15). Batch at half price (10). Official SDKs in seven languages (10). Documented errors, retry-after and retries (15). 15 + 15 + 15 + 15 + 10 + 10 + 15 = 95.

Glimpse 20

Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). On 17 October the tool, tool_choice, response_format, structured_outputs, cached-price, context, output-limit and batch readings for this model all came from OpenRouter's endpoints API, which this run doesn't use, so they are struck. No readable first-hand page states them today. Elorian's docs sit on a host that refuses our crawler, and Together's model page says only text, image and video in and text out on a dedicated deployment. Tool use (0 of 20), structured output (0 of 15), prompt caching (0 of 15), context length (0 of 15), batch (0 of 10). OpenRouter's SDKs in TypeScript, Python and Go, and any OpenAI client works (10 of 10, per the 17 October check, not re-read on 4 November 2026). OpenRouter's documented error codes with limit_source and remedy hints, nothing specific to video or image limits (10 of 15, per the 17 October check, not re-read on 4 November 2026). 0 + 0 + 0 + 0 + 0 + 10 + 10 = 20.

Claude Mythos 5.2 90

Model reading for claude-mythos-5-2 on the Claude API. Platform facts are the Claude API listing's (anthropic-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. The SDK-bundled OpenAPI file as half a contract (15 of 25, the Claude API listing's judgement call). llms.txt with Markdown twins (10). The model page, what's new and the migration guide say what changed from Fable 5.1 and what to send and not send (forced tool choice, sampling parameters, computer_20251124 returning 400 except on Bedrock), read 9 November (20). Structured outputs and strict tools GA (15). Documented error types with request_id (15). anthropic-version and dated release notes (15). 15 + 10 + 20 + 15 + 15 + 15 = 90.

Glimpse 40

Model reading. Elorian publishes no API reference, model card or llms.txt in public. Its docs sit at platform.elorian.ai/docs, a host whose robots.txt answers access denied. The 17 October contract reading rested on OpenRouter's OpenAPI-documented chat endpoint, with no recorded visible download link on a host now paused, and on the parameter list from OpenRouter's endpoints API, both struck (0 of 25). OpenRouter's llms.txt and Markdown docs, including video input (10, per the 17 October check, not re-read on 4 November 2026). The launch post and Together's model page name the jobs (visual search, video captioning, dense counting, robotics planning) and the post states limits (token cost, no action outputs yet), but nothing says when not to use it or how video is sampled (6 of 20). Typed parameters for OpenRouter's chat endpoint in its API reference, with no reasoning effort levels documented for this model (10 of 15, per the 17 October check, not re-read on 4 November 2026; the 17 October tool_choice reading came from the struck endpoints API). OpenRouter's examples and error reference, with no Glimpse-specific examples or limits on video length or image count (7 of 15). OpenRouter's dated changelog, with no changelog from Elorian (7 of 15, held as partly met; the dated canonical slug came from the struck endpoints API). 0 + 10 + 6 + 10 + 7 + 7 = 40.

Claude Mythos 5.2 85

Model reading for claude-mythos-5-2 on the Claude API. Platform facts are the Claude API listing's (anthropic-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Commercial Terms with named contracting parties and Apache 2.0 SDKs (15). Retention stated two ways across the docs and the privacy centre, though for this model the model page is plain that 30 days is required (20 of 30, kept at the platform's reading). Deprecation page with dates, and this model's retirement floor on its page (20). Processing countries and subprocessors named (20). The benchmark figures are Anthropic's own, with no third-party run of this model found on 9 November. 15 + 20 + 20 + 20 = 75.

Glimpse 38

Closed model with weights not released and the open-weight base model unnamed. Elorian's terms sit on platform.elorian.ai, whose robots.txt answers access denied, so they were not read; published terms on a refusing host keep the closed-service value, held at 13 of 30. The privacy policy says Elorian trains on submitted content from free use and gives no retention periods, and the acceptable use policy, updated 19 October 2026, is still titled Privacy Policy and still carries a drafting comment from a terms outline in its markup (10 of 30, held as partly met; the 17 October comparison with the terms rested on the struck script reading). No deprecation policy or dated notices (0 of 20). Services hosted in the United States and subprocessors named by category only, and OpenRouter shows Together as the provider with its data policy (8 of 20). 13 + 10 + 0 + 8 = 31.

Claude Mythos 5.2 91

Model reading for claude-mythos-5-2 on the Claude API. Platform facts are the Claude API listing's (anthropic-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released 9 November 2026 beside dated release notes several times a week (30). 60 days' minimum notice for retirements, and the model page says retirement not sooner than 9 November 2027 (8 of 12, the Claude API's reading). Model shutdowns kept to notice (8). Support centre and dated notes (15). The sampled SDK issue without a reply, per the 1 October check (5 of 10). Current SDKs (15). Runtimes stated (10). 30 + 8 + 8 + 15 + 5 + 15 + 10 = 91.

Glimpse 51

Model reading. Announced on 16 October 2026, 19 days before 4 November, and still labelled a research preview on Together's model page that day (30). One release, no history of versions or retirements and no deprecation notice period (3 of 20). Elorian's support page says there is no support queue, and channels are email and a Discord server, not tested (6 of 25, per the 17 October check, not re-read on 4 November 2026; the terms' no-support clause came from the struck script reading). No official SDK from Elorian. OpenRouter's SDKs are current (8 of 15). No package or CI of Elorian's to read. OpenRouter's SDK repositories run CI (4 of 10). 30 + 3 + 6 + 8 + 4 = 51.

Claude Mythos 5.2 60

Model reading for claude-mythos-5-2 on the Claude API. Platform facts are the Claude API listing's (anthropic-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at status.claude.com with component history (20). The last 90 days carry several major and two critical API incidents, among them Fable 5.1 and Mythos 5.1 on 3 September and Fable 5.1 on 23 and 25 October, so 0 for incident history. Rate limits published per model, Fable 5.x at 4,000 requests a minute at the Start tier (15). 429s with retry-after and SDK retries with backoff (15). No SLA on sale (0). The model page lists it as a current model with no preview label (10). 20 + 0 + 15 + 15 + 0 + 10 = 60. Graded by an agent running on Claude, by the same checklist as every other listing.

Glimpse 23

Hosted lines, read on the OpenRouter route. OpenRouter's status host refuses our crawler in robots.txt, so the 17 October reading of it is struck, and Elorian has no status page found (0 of 20). No 90-day incident record could be read. The 17 October uptime figures came from OpenRouter's endpoints API, a JSON data API this run doesn't use, and are struck (5). OpenRouter's limits page documents credit, budget and rate limits and a key endpoint that reports what's left, but sets no request cap on paid models, and no limit for Glimpse was found (8 of 15, per the 17 October check, not re-read on 4 November 2026, openrouter.ai paused on its terms). The errors page documents Retry-After on 429 and 503 and on 402 in-flight budget errors, and says the official SDKs honour it, with no safe-retry guidance or idempotency keys recorded (10, Retry-After alone, the value this run gives backoff or Retry-After guidance by itself; per the 17 October check, not re-read on 4 November 2026). No SLA from Elorian or for this endpoint (0). Elorian and Together label Glimpse a research preview (0). 0 + 5 + 8 + 10 + 0 + 0 = 23.

Claude Mythos 5.2 92

Model reading for claude-mythos-5-2 on the Claude API. Platform facts are the Claude API listing's (anthropic-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Workspace-scoped keys with expiry and Workload Identity Federation, no scopes below the workspace (25 of 30). No training on API data without express permission (20). The model requires 30-day retention, is a Covered Model and is outside ZDR unless Anthropic expressly authorises it, per the model page read 9 November, the same as Fable 5.1 (12 of 15). Usage and cost analytics, Compliance API and OpenTelemetry export (15). security.txt, HackerOne and SOC 2, ISO 27001 and ISO 42001 (20). Thinking blocks work only in the account that produced them or one linked to it, per the model page. 25 + 20 + 12 + 15 + 20 = 92.

Glimpse 56

Model reading. OpenRouter bearer keys with per-key credit limits, management keys and OAuth PKCE, no permission scopes (25 of 30, per the 17 October check, not re-read on 4 November 2026). Training on API data on this route is off according to OpenRouter's policy display for Together (no training, no prompt retention). Elorian's privacy policy trains on Inputs and Outputs from free access by default and says different terms may apply to paid and API use. The 17 October reading of Elorian's terms came from a script on a host that now refuses our crawler and is struck. Whether Elorian receives prompts from the Together deployment was not established (8 of 20, held as partly met). OpenRouter's zero-retention filter and Together's no-retention flag, against Elorian's retention 'for as long as reasonably necessary' with no period (8 of 15). OpenRouter's per-generation activity records for the operator (10 of 15). OpenRouter's security.txt was valid at its last check. Elorian has no security.txt, disclosure policy, bug bounty or certification found (5 of 20, held as partly met). 25 + 8 + 8 + 10 + 5 = 56. Readings of OpenRouter and Elorian pages per the 17 October check, not re-read on 4 November 2026.