{ "schema_version": 1, "generated_at": "2026-10-08T13:18:22Z", "data_hash": "80d6499a40b843d3", "site": { "title": "AI AI Model Benchmark", "tagline": "Frontier models tested in real agentic harnesses, at max effort, reviewed honestly.", "base_url": "https://model-review-3yp.pages.dev/" }, "wave": { "number": 3, "status": "Wave 1 and phase B done; wave 3 in progress", "prompts": [ "ps5_controller", "pelican_bicycle", "macbook_pro_16", "lighthouse_night", "isometric_town", "pelican_bicycle_animated", "brown_pelican_detailed", "xbox360_controller", "bmw_m4_side" ], "progress": [ { "prompt_id": "ps5_controller", "title": "DualSense controller, max fidelity", "planned": 16, "done": 18, "ok": 16, "raw": 15, "not_tested": 2, "pending": 1 }, { "prompt_id": "pelican_bicycle", "title": "Pelican riding a bicycle (control)", "planned": 16, "done": 20, "ok": 20, "raw": 2, "not_tested": 2, "pending": 0 }, { "prompt_id": "macbook_pro_16", "title": "MacBook Pro 16\" realistic 3D render (Playcode benchmark)", "planned": 16, "done": 19, "ok": 18, "raw": 1, "not_tested": 2, "pending": 0 }, { "prompt_id": "lighthouse_night", "title": "Lighthouse on a headland at night", "planned": 16, "done": 19, "ok": 17, "raw": 2, "not_tested": 2, "pending": 0 }, { "prompt_id": "isometric_town", "title": "Isometric SVG town with sprite sheet", "planned": 16, "done": 20, "ok": 18, "raw": 1, "not_tested": 2, "pending": 0 }, { "prompt_id": "pelican_bicycle_animated", "title": "Animated pelican riding a bicycle (SMIL/CSS)", "planned": 16, "done": 18, "ok": 18, "raw": 1, "not_tested": 2, "pending": 1 }, { "prompt_id": "brown_pelican_detailed", "title": "California brown pelican riding a bicycle (detailed spec)", "planned": 16, "done": 17, "ok": 16, "raw": 1, "not_tested": 2, "pending": 2 }, { "prompt_id": "xbox360_controller", "title": "Xbox 360 controller", "planned": 16, "done": 17, "ok": 17, "raw": 1, "not_tested": 2, "pending": 2 }, { "prompt_id": "bmw_m4_side", "title": "BMW M4 Competition, side view (flat vector)", "planned": 16, "done": 17, "ok": 16, "raw": 1, "not_tested": 1, "pending": 2 } ] }, "not_tested": { "status": "no_access", "label": "Not tested (no access)", "slots": [ { "prompt_id": "ps5_controller", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "ps5_controller", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "pelican_bicycle", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "pelican_bicycle", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "macbook_pro_16", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "macbook_pro_16", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "lighthouse_night", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "lighthouse_night", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "isometric_town", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "isometric_town", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "pelican_bicycle_animated", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "pelican_bicycle_animated", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "brown_pelican_detailed", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "brown_pelican_detailed", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "xbox360_controller", "model_id": "gemini-3.8-flash", "track": "home" }, { "prompt_id": "xbox360_controller", "model_id": "gemini-3.8-flash", "track": "neutral" }, { "prompt_id": "bmw_m4_side", "model_id": "gemini-3.8-flash", "track": "home" } ], "models": [ { "id": "gemini-3.8-flash", "name": "Gemini 3.8 Flash" } ] }, "pending": { "status": "pending", "label": "Pending — queued, not run yet", "slots": [ { "id": "blender_donut__claude-code__claude-fable-5-1", "prompt_id": "blender_donut", "model_id": "claude-fable-5-1", "harness": "Claude Code", "track": "home", "repeat": null }, { "id": "blender_donut__codex__gpt-6-astra", "prompt_id": "blender_donut", "model_id": "gpt-6-astra", "harness": "Codex CLI", "track": "home", "repeat": null }, { "id": "blender_donut__dsh__deepseek-flash", "prompt_id": "blender_donut", "model_id": "deepseek-flash", "harness": "dsh", "track": "home", "repeat": null }, { "id": "blender_donut__kimi-code__kimi-k3", "prompt_id": "blender_donut", "model_id": "kimi-k3", "harness": "Kimi Code CLI", "track": "home", "repeat": null }, { "id": "blender_donut__opencode__claude-fable-5-1", "prompt_id": "blender_donut", "model_id": "claude-fable-5-1", "harness": "OpenCode", "track": "neutral", "repeat": null }, { "id": "blender_donut__opencode__claude-opus-5-5", "prompt_id": "blender_donut", "model_id": "claude-opus-5-5", "harness": "OpenCode", "track": "neutral", "repeat": null }, { "id": "blender_donut__opencode__deepseek-flash", "prompt_id": "blender_donut", "model_id": "deepseek-flash", "harness": "OpenCode", "track": "neutral", "repeat": null }, { "id": "blender_donut__opencode__gpt-6-astra", "prompt_id": "blender_donut", "model_id": "gpt-6-astra", "harness": "OpenCode", "track": "neutral", "repeat": null }, { "id": "blender_donut__opencode__kimi-k3", "prompt_id": "blender_donut", "model_id": "kimi-k3", "harness": "OpenCode", "track": "neutral", "repeat": null }, { "id": "bmw_m4_side__grok-build__grok-4.7", "prompt_id": "bmw_m4_side", "model_id": "grok-4.7", "harness": "Grok Build", "track": "home", "repeat": null }, { "id": "bmw_m4_side__opencode__grok-4.7", "prompt_id": "bmw_m4_side", "model_id": "grok-4.7", "harness": "OpenCode", "track": "neutral", "repeat": null }, { "id": "brown_pelican_detailed__grok-build__grok-4.7", "prompt_id": "brown_pelican_detailed", "model_id": "grok-4.7", "harness": "Grok Build", "track": "home", "repeat": null }, { "id": "brown_pelican_detailed__opencode__grok-4.7", "prompt_id": "brown_pelican_detailed", "model_id": "grok-4.7", "harness": "OpenCode", "track": "neutral", "repeat": null }, { "id": "lighthouse_night__grok-build__grok-4.7__repeat2", "prompt_id": "lighthouse_night", "model_id": "grok-4.7", "harness": "Grok Build", "track": "home", "repeat": "repeat2" }, { "id": "pelican_bicycle__grok-build__grok-4.7__repeat2", "prompt_id": "pelican_bicycle", "model_id": "grok-4.7", "harness": "Grok Build", "track": "home", "repeat": "repeat2" }, { "id": "pelican_bicycle_animated__grok-build__grok-4.7", "prompt_id": "pelican_bicycle_animated", "model_id": "grok-4.7", "harness": "Grok Build", "track": "home", "repeat": null }, { "id": "ps5_controller__grok-build__grok-4.7", "prompt_id": "ps5_controller", "model_id": "grok-4.7", "harness": "Grok Build", "track": "home", "repeat": null }, { "id": "xbox360_controller__grok-build__grok-4.7", "prompt_id": "xbox360_controller", "model_id": "grok-4.7", "harness": "Grok Build", "track": "home", "repeat": null }, { "id": "xbox360_controller__opencode__grok-4.7", "prompt_id": "xbox360_controller", "model_id": "grok-4.7", "harness": "OpenCode", "track": "neutral", "repeat": null } ] }, "infra": { "label": "Infrastructure failures (not model results)", "items": [ { "id": "macbook_pro_16__opencode__deepseek-flash__attempt1", "cell": "macbook_pro_16__opencode__deepseek-flash", "attempt": 1, "result_id": "macbook_pro_16__opencode__deepseek-flash", "prompt_id": "macbook_pro_16", "model": "DeepSeek V4.1 Flash", "model_id": "deepseek-flash", "harness": "OpenCode 1.18.32", "harness_family": "OpenCode", "track": "neutral", "effort": "max", "run_date": "2026-09-23", "started_utc": "2026-09-23T23:23:46Z", "wall_time_s": 1832.3, "note": "Infrastructure failure, not a model result: the prompt was never delivered, because the harness was not ready when the runner sent it, and the run was stopped after 30 minutes without progress. The cell was re-run.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "pelican_bicycle__claude-code__glm-5.3__attempt1", "cell": "pelican_bicycle__claude-code__glm-5.3", "attempt": 1, "result_id": "pelican_bicycle__claude-code__glm-5.3__attempt2", "prompt_id": "pelican_bicycle", "model": "GLM-5.3", "model_id": "glm-5.3", "harness": "Claude Code 2.1.280", "harness_family": "Claude Code", "track": "home", "effort": "max", "run_date": "2026-09-24", "started_utc": "2026-09-24T03:48:19Z", "wall_time_s": 386.4, "note": "Infrastructure failure, not a model result: the runner addressed the Claude Code tmux session by a name containing \".\" (glm-5.3), which tmux reads as a window.pane separator, so the prompt was never delivered and 0 tokens reached the model ($0). Runner bug fixed 05:06Z; cell re-run.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "pelican_bicycle__claude-code__glm-5.3__infra__attempt2", "cell": "pelican_bicycle__claude-code__glm-5.3", "attempt": 2, "result_id": "pelican_bicycle__claude-code__glm-5.3__attempt2", "prompt_id": "pelican_bicycle", "model": "GLM-5.3", "model_id": "glm-5.3", "harness": "Claude Code 2.1.280", "harness_family": "Claude Code", "track": "home", "effort": "max", "run_date": "2026-09-24", "started_utc": "2026-09-24T04:50:51Z", "wall_time_s": 386.4, "note": "Infrastructure failure, not a model result: the runner addressed the Claude Code tmux session by a name containing \".\" (glm-5.3), which tmux reads as a window.pane separator, so the prompt was never delivered and 0 tokens reached the model ($0). Runner bug fixed 05:06Z; cell re-run.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "pelican_bicycle_animated__grok-build__grok-4.7__attempt1", "cell": "pelican_bicycle_animated__grok-build__grok-4.7", "attempt": 1, "result_id": null, "prompt_id": "pelican_bicycle_animated", "model": "Grok 4.7", "model_id": "grok-4.7", "harness": "Grok Build 1.0.41", "harness_family": "Grok Build", "track": "home", "effort": "xhigh", "run_date": "2026-09-24", "started_utc": "2026-09-24T09:46:00Z", "wall_time_s": 21.2, "note": "Infrastructure failure, not a model result: the provider stopped serving requests mid-run. No tokens were used and nothing was produced.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "ps5_controller__claude-code__glm-5.3__attempt1", "cell": "ps5_controller__claude-code__glm-5.3", "attempt": 1, "result_id": "ps5_controller__claude-code__glm-5.3__attempt2", "prompt_id": "ps5_controller", "model": "GLM-5.3", "model_id": "glm-5.3", "harness": "Claude Code 2.1.280", "harness_family": "Claude Code", "track": "home", "effort": "max", "run_date": "2026-09-24", "started_utc": "2026-09-24T11:23:05Z", "wall_time_s": 573.1, "note": "Infra failure, not a model DNF: after 8.5 min the Fireworks stream ended with 'API Error: Stream ended without receiving any events' (1.2k input / 14 output tokens, 0 tool calls, no artifact). Re-queued as a re-run.", "cost_usd": 0.001742, "cost_basis": "estimated_from_list_price", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "brown_pelican_detailed__kimi-code__kimi-k3__attempt1", "cell": "brown_pelican_detailed__kimi-code__kimi-k3", "attempt": 1, "result_id": "brown_pelican_detailed__kimi-code__kimi-k3__attempt2", "prompt_id": "brown_pelican_detailed", "model": "Kimi K3", "model_id": "kimi-k3", "harness": "Kimi Code CLI 2.1.0", "harness_family": "Kimi Code CLI", "track": "home", "effort": "max", "run_date": "2026-09-24", "started_utc": "2026-09-24T11:33:40Z", "wall_time_s": 1042.7, "note": "Infra failure, not a model DNF: after 17 min of reasoning (about 95k characters) the model wrote one line (\"I'll create this SVG step by step:\") and the response stream closed with no tool call and no final usage record, so no brown_pelican.svg was written. Every other completed step on this endpoint across the 7 Kimi Code runs reported usage; this one reported 0 input / 0 output, which marks a truncated stream. Kimi Code's own local count put the context at about 24.6k tokens. Not re-run yet.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "bmw_m4_side__cline__gemini-3.8-flash__attempt1", "cell": "bmw_m4_side__cline__gemini-3.8-flash", "attempt": 1, "result_id": "bmw_m4_side__cline__gemini-3.8-flash__attempt2", "prompt_id": "bmw_m4_side", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:03:09Z", "wall_time_s": 49.9, "note": "After 50 s the Cline gateway (Vercel -> Google) answered HTTP 400 'Request contains an invalid argument' (one Vertex attempt inside it gave 503); Cline ended the run. Upstream gateway failure (the same error on attempt 4 shows the chain: Cline's Google key over quota 429 -> Vertex 503 -> final fallback 400); not a model failure.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "bmw_m4_side__cline__gemini-3.8-flash__attempt3", "cell": "bmw_m4_side__cline__gemini-3.8-flash", "attempt": 3, "result_id": "bmw_m4_side__cline__gemini-3.8-flash__attempt2", "prompt_id": "bmw_m4_side", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:16:27Z", "wall_time_s": 1313, "note": "After 103 iterations (22 min, no bmw_m4.svg written yet) the Cline gateway (Vercel -> Google) answered HTTP 400 'Request contains an invalid argument'; Cline ended the run. Upstream gateway failure (the same error on attempt 4 shows the chain: Cline's Google key over quota 429 -> Vertex 503 -> final fallback 400); not a model failure. (Record salvaged by hand: the runner's ledger step crashed on this attempt; fixed.)", "cost_usd": 0.0, "cost_basis": "estimated_from_list_price", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "bmw_m4_side__cline__gemini-3.8-flash__attempt4", "cell": "bmw_m4_side__cline__gemini-3.8-flash", "attempt": 4, "result_id": "bmw_m4_side__cline__gemini-3.8-flash__attempt2", "prompt_id": "bmw_m4_side", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:39:29Z", "wall_time_s": 47.7, "note": "Cline free tier answered a rate limit / quota error ('quota'); upstream of the harness, not a model failure. [Reclassified 2026-09-24T20:05Z from INFRASTRUCTURE: a 429 quota refusal is QUOTA and does not count against the row.]", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__gemini-3.8-flash__infra__attempt1", "cell": "pelican_bicycle_animated__cline__gemini-3.8-flash", "attempt": 1, "result_id": "pelican_bicycle_animated__cline__gemini-3.8-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:50:48Z", "wall_time_s": 158.6, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (provider attempts: Google 400 'invalid argument' / Vertex 503 'temporarily unavailable'); Cline ended the run. Upstream of the harness, not a model failure.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "pelican_bicycle_animated__cline__gemini-3.8-flash__attempt2", "cell": "pelican_bicycle_animated__cline__gemini-3.8-flash", "attempt": 2, "result_id": "pelican_bicycle_animated__cline__gemini-3.8-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:55:39Z", "wall_time_s": 48.2, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (provider attempts: Google 400 'invalid argument' / Vertex 503 'temporarily unavailable'); Cline ended the run. Upstream of the harness, not a model failure.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "brown_pelican_detailed__cline__gemini-3.8-flash__attempt1", "cell": "brown_pelican_detailed__cline__gemini-3.8-flash", "attempt": 1, "result_id": "brown_pelican_detailed__cline__gemini-3.8-flash", "prompt_id": "brown_pelican_detailed", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:56:29Z", "wall_time_s": 72.5, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (provider attempts: Google 400 'invalid argument' / Vertex 503 'temporarily unavailable'); Cline ended the run. Upstream of the harness, not a model failure.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "xbox360_controller__cline__gemini-3.8-flash__attempt1", "cell": "xbox360_controller__cline__gemini-3.8-flash", "attempt": 1, "result_id": "xbox360_controller__cline__gemini-3.8-flash", "prompt_id": "xbox360_controller", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:57:45Z", "wall_time_s": 43.5, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (provider attempts: Google 400 'invalid argument' / Vertex 503 'temporarily unavailable'); Cline ended the run. Upstream of the harness, not a model failure.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "lighthouse_night__cline__gemini-3.8-flash__attempt1", "cell": "lighthouse_night__cline__gemini-3.8-flash", "attempt": 1, "result_id": "lighthouse_night__cline__gemini-3.8-flash", "prompt_id": "lighthouse_night", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:58:35Z", "wall_time_s": 23.2, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (provider attempts: Google 400 'invalid argument' / Vertex 503 'temporarily unavailable'); Cline ended the run. Upstream of the harness, not a model failure.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "macbook_pro_16__cline__gemini-3.8-flash__attempt1", "cell": "macbook_pro_16__cline__gemini-3.8-flash", "attempt": 1, "result_id": "macbook_pro_16__cline__gemini-3.8-flash__attempt2", "prompt_id": "macbook_pro_16", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T18:59:01Z", "wall_time_s": 263.7, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (provider attempts: Google 400 'invalid argument' / Vertex 503 'temporarily unavailable'); Cline ended the run. Upstream of the harness, not a model failure.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "pelican_bicycle_animated__cline__gemini-3.8-flash__attempt3", "cell": "pelican_bicycle_animated__cline__gemini-3.8-flash", "attempt": 3, "result_id": "pelican_bicycle_animated__cline__gemini-3.8-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T19:03:27Z", "wall_time_s": 284.7, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (Vertex 503 'temporarily unavailable', then Google 400 'invalid argument'); Cline ended the run (exit 1). A pelican_animated.svg existed when the run was cut (kept for reference, not a finished result). Not a model failure. First filed as MODEL/dnf by the runner, reclassified.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "xbox360_controller__cline__gemini-3.8-flash__attempt2", "cell": "xbox360_controller__cline__gemini-3.8-flash", "attempt": 2, "result_id": "xbox360_controller__cline__gemini-3.8-flash", "prompt_id": "xbox360_controller", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T19:17:30Z", "wall_time_s": 216.7, "note": "Cline's gateway (Vercel -> Google/Vertex) failed the request mid-run (provider attempts: Google 400 'invalid argument' / Vertex 503 'temporarily unavailable'); Cline ended the run. Upstream of the harness, not a model failure. A xbox360.svg existed when the run was cut (kept for reference, not a finished result).", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "INFRA" }, { "id": "fjord__cline__gemini-3.8-flash__attempt1", "cell": "fjord__cline__gemini-3.8-flash", "attempt": 1, "result_id": null, "prompt_id": "fjord", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T19:53:49Z", "wall_time_s": 7.6, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached before the run could start ('Daily free model limit reached … Try again in 21h 53m', ~17:47Z 2026-09-25). Not a model failure; first filed as MODEL/dnf by the runner, reclassified.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "ps5_controller__cline__gemini-3.8-flash__infra__attempt2", "cell": "ps5_controller__cline__gemini-3.8-flash", "attempt": 2, "result_id": "ps5_controller__cline__gemini-3.8-flash__attempt2", "prompt_id": "ps5_controller", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T19:53:59Z", "wall_time_s": 8.6, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached before the run could start ('Daily free model limit reached … Try again in 21h 53m', ~17:47Z 2026-09-25). Not a model failure; first filed as MODEL/dnf by the runner, reclassified.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "isometric_town__cline__gemini-3.8-flash__attempt2", "cell": "isometric_town__cline__gemini-3.8-flash", "attempt": 2, "result_id": "isometric_town__cline__gemini-3.8-flash__attempt1", "prompt_id": "isometric_town", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T19:54:12Z", "wall_time_s": 8.0, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached before the run could start ('Daily free model limit reached … Try again in 21h 53m', ~17:47Z 2026-09-25). Not a model failure; first filed as MODEL/dnf by the runner, reclassified.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "js_short__cline__gemini-3.8-flash__attempt2", "cell": "js_short__cline__gemini-3.8-flash", "attempt": 2, "result_id": null, "prompt_id": "js_short", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T19:54:23Z", "wall_time_s": 7.8, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached before the run could start ('Daily free model limit reached … Try again in 21h 53m', ~17:47Z 2026-09-25). Not a model failure; first filed as MODEL/dnf by the runner, reclassified.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__infra__attempt1", "cell": "pelican_bicycle_animated__cline__deepseek-v4.1-flash", "attempt": 1, "result_id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "DeepSeek V4.1 Flash", "model_id": "deepseek-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T20:25:49Z", "wall_time_s": 437.5, "note": "Cline's daily free-usage limit for cline-free/deepseek-v4.1-flash was reached ('daily free model limit'); resets in about 23h 22m (~2026-09-25T19:55:07Z). Quota, not a model failure; does not count against the row's attempts. A pelican_animated.svg existed when the run was cut (kept for reference, not a finished result).", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "macbook_pro_16__cline__gemini-3.8-flash__attempt3", "cell": "macbook_pro_16__cline__gemini-3.8-flash", "attempt": 3, "result_id": "macbook_pro_16__cline__gemini-3.8-flash__attempt2", "prompt_id": "macbook_pro_16", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T21:21:43Z", "wall_time_s": 7.7, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached ('daily free model limit'); resets in about 20h 26m (~2026-09-25T17:47:50Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt2", "cell": "pelican_bicycle_animated__cline__deepseek-v4.1-flash", "attempt": 2, "result_id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "DeepSeek V4.1 Flash", "model_id": "deepseek-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T22:12:56Z", "wall_time_s": 7.7, "note": "Cline's daily free-usage limit for cline-free/deepseek-v4.1-flash was reached ('daily free model limit'); resets in about 21h 42m (~2026-09-25T19:55:04Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__mimo-v2.6-flash__infra__attempt1", "cell": "pelican_bicycle_animated__cline__mimo-v2.6-flash", "attempt": 1, "result_id": "pelican_bicycle_animated__cline__mimo-v2.6-flash__attempt2", "prompt_id": "pelican_bicycle_animated", "model": "MiMo V2.6 Flash", "model_id": "mimo-v2.6-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T22:13:07Z", "wall_time_s": 2601.3, "note": "Cline's daily free-usage limit for cline-free/mimo-v2.6-flash was reached ('daily free model limit'); resets in about 21h 41m (~2026-09-25T20:37:28Z). Quota, not a model failure; does not count against the row's attempts. A pelican_animated.svg existed when the run was cut (kept for reference, not a finished result).", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "macbook_pro_16__cline__gemini-3.8-flash__attempt4", "cell": "macbook_pro_16__cline__gemini-3.8-flash", "attempt": 4, "result_id": "macbook_pro_16__cline__gemini-3.8-flash__attempt2", "prompt_id": "macbook_pro_16", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T22:56:45Z", "wall_time_s": 9.0, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached ('daily free model limit'); resets in about 18h 50m (~2026-09-25T17:46:54Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle__cline__muse-spark-1.3__attempt1", "cell": "pelican_bicycle__cline__muse-spark-1.3", "attempt": 1, "result_id": "pelican_bicycle__cline__muse-spark-1.3", "prompt_id": "pelican_bicycle", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T22:56:58Z", "wall_time_s": 9.7, "note": "Cline's free route answered a quota / rate-limit refusal ('429'); model held until 2026-09-24T23:02:08Z. Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle__cline__muse-spark-1.3__attempt2", "cell": "pelican_bicycle__cline__muse-spark-1.3", "attempt": 2, "result_id": "pelican_bicycle__cline__muse-spark-1.3", "prompt_id": "pelican_bicycle", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:03:53Z", "wall_time_s": 49.3, "note": "Cline's free route answered a quota / rate-limit refusal ('429'); model held until 2026-09-24T23:09:42Z. Quota, not a model failure; does not count against the row's attempts.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle__cline__muse-spark-1.3__attempt3", "cell": "pelican_bicycle__cline__muse-spark-1.3", "attempt": 3, "result_id": "pelican_bicycle__cline__muse-spark-1.3", "prompt_id": "pelican_bicycle", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:09:58Z", "wall_time_s": 14.4, "note": "Cline's free route answered a quota / rate-limit refusal ('status 429'); model held until 2026-09-24T23:15:12Z. Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt3", "cell": "pelican_bicycle_animated__cline__deepseek-v4.1-flash", "attempt": 3, "result_id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "DeepSeek V4.1 Flash", "model_id": "deepseek-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:16:55Z", "wall_time_s": 7.8, "note": "Cline's daily free-usage limit for cline-free/deepseek-v4.1-flash was reached ('daily free model limit'); resets in about 20h 38m (~2026-09-25T19:55:03Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle__cline__muse-spark-1.3__attempt4", "cell": "pelican_bicycle__cline__muse-spark-1.3", "attempt": 4, "result_id": "pelican_bicycle__cline__muse-spark-1.3", "prompt_id": "pelican_bicycle", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:17:05Z", "wall_time_s": 64.3, "note": "Cline's free route answered a quota / rate-limit refusal ('status 429'); model held until 2026-09-24T23:23:10Z. Quota, not a model failure; does not count against the row's attempts.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "brown_pelican_detailed__cline__muse-spark-1.3__attempt1", "cell": "brown_pelican_detailed__cline__muse-spark-1.3", "attempt": 1, "result_id": "brown_pelican_detailed__cline__muse-spark-1.3", "prompt_id": "brown_pelican_detailed", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:48:11Z", "wall_time_s": 18.9, "note": "Cline's free route answered a quota / rate-limit refusal ('status 429'); model held until 2026-09-24T23:53:30Z. Quota, not a model failure; does not count against the row's attempts.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "brown_pelican_detailed__cline__muse-spark-1.3__attempt2", "cell": "brown_pelican_detailed__cline__muse-spark-1.3", "attempt": 2, "result_id": "brown_pelican_detailed__cline__muse-spark-1.3", "prompt_id": "brown_pelican_detailed", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:53:39Z", "wall_time_s": 8.3, "note": "Cline's free route answered a quota / rate-limit refusal ('status 429'); model held until 2026-09-24T23:58:48Z. Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__mimo-v2.6-flash__infra__attempt2", "cell": "pelican_bicycle_animated__cline__mimo-v2.6-flash", "attempt": 2, "result_id": "pelican_bicycle_animated__cline__mimo-v2.6-flash__attempt2", "prompt_id": "pelican_bicycle_animated", "model": "MiMo V2.6 Flash", "model_id": "mimo-v2.6-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:56:29Z", "wall_time_s": 8.5, "note": "Cline's daily free-usage limit for cline-free/mimo-v2.6-flash was reached ('daily free model limit'); resets in about 20h 41m (~2026-09-25T20:37:38Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "macbook_pro_16__cline__gemini-3.8-flash__attempt5", "cell": "macbook_pro_16__cline__gemini-3.8-flash", "attempt": 5, "result_id": "macbook_pro_16__cline__gemini-3.8-flash__attempt2", "prompt_id": "macbook_pro_16", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:56:55Z", "wall_time_s": 8.5, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached ('daily free model limit'); resets in about 17h 50m (~2026-09-25T17:47:03Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "brown_pelican_detailed__cline__muse-spark-1.3__attempt3", "cell": "brown_pelican_detailed__cline__muse-spark-1.3", "attempt": 3, "result_id": "brown_pelican_detailed__cline__muse-spark-1.3", "prompt_id": "brown_pelican_detailed", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-24", "started_utc": "2026-09-24T23:58:49Z", "wall_time_s": 20.1, "note": "Cline's free route answered a quota / rate-limit refusal ('status 429'); model held until 2026-09-25T00:04:09Z. Quota, not a model failure; does not count against the row's attempts.", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "lighthouse_night__cline__muse-spark-1.3__attempt1", "cell": "lighthouse_night__cline__muse-spark-1.3", "attempt": 1, "result_id": "lighthouse_night__cline__muse-spark-1.3", "prompt_id": "lighthouse_night", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-25", "started_utc": "2026-09-25T00:11:59Z", "wall_time_s": 207.1, "note": "Cline's free route answered a quota / rate-limit refusal ('status 429'); model held until 2026-09-25T00:20:27Z. Quota, not a model failure; does not count against the row's attempts. A lighthouse.svg existed when the run was cut (kept for reference, not a finished result).", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt4", "cell": "pelican_bicycle_animated__cline__deepseek-v4.1-flash", "attempt": 4, "result_id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "DeepSeek V4.1 Flash", "model_id": "deepseek-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-25", "started_utc": "2026-09-25T00:17:04Z", "wall_time_s": 8.5, "note": "Cline's daily free-usage limit for cline-free/deepseek-v4.1-flash was reached ('daily free model limit'); resets in about 19h 38m (~2026-09-25T19:55:13Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "lighthouse_night__cline__muse-spark-1.3__attempt2", "cell": "lighthouse_night__cline__muse-spark-1.3", "attempt": 2, "result_id": "lighthouse_night__cline__muse-spark-1.3", "prompt_id": "lighthouse_night", "model": "Muse Spark 1.3", "model_id": "muse-spark-1.3", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-25", "started_utc": "2026-09-25T00:20:28Z", "wall_time_s": 215.0, "note": "Cline's free route answered a quota / rate-limit refusal ('429'); model held until 2026-09-25T00:29:03Z. Quota, not a model failure; does not count against the row's attempts. A lighthouse.svg existed when the run was cut (kept for reference, not a finished result).", "cost_usd": 0, "cost_basis": "reported_by_harness", "usage_not_reported": false, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "macbook_pro_16__cline__gemini-3.8-flash__attempt6", "cell": "macbook_pro_16__cline__gemini-3.8-flash", "attempt": 6, "result_id": "macbook_pro_16__cline__gemini-3.8-flash__attempt2", "prompt_id": "macbook_pro_16", "model": "Gemini 3.8 Flash", "model_id": "gemini-3.8-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-25", "started_utc": "2026-09-25T01:19:33Z", "wall_time_s": 7.8, "note": "Cline's daily free-usage limit for cline-free/gemini-3.8-flash was reached ('daily free model limit'); resets in about 16h 28m (~2026-09-25T17:47:41Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt5", "cell": "pelican_bicycle_animated__cline__deepseek-v4.1-flash", "attempt": 5, "result_id": "pelican_bicycle_animated__cline__deepseek-v4.1-flash__attempt1", "prompt_id": "pelican_bicycle_animated", "model": "DeepSeek V4.1 Flash", "model_id": "deepseek-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-25", "started_utc": "2026-09-25T01:19:43Z", "wall_time_s": 7.9, "note": "Cline's daily free-usage limit for cline-free/deepseek-v4.1-flash was reached ('daily free model limit'); resets in about 18h 36m (~2026-09-25T19:55:51Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "pelican_bicycle_animated__cline__mimo-v2.6-flash__attempt3", "cell": "pelican_bicycle_animated__cline__mimo-v2.6-flash", "attempt": 3, "result_id": "pelican_bicycle_animated__cline__mimo-v2.6-flash__attempt2", "prompt_id": "pelican_bicycle_animated", "model": "MiMo V2.6 Flash", "model_id": "mimo-v2.6-flash", "harness": "Cline CLI 3.0.65", "harness_family": "Cline CLI", "track": "neutral", "effort": "high", "run_date": "2026-09-25", "started_utc": "2026-09-25T01:19:54Z", "wall_time_s": 7.5, "note": "Cline's daily free-usage limit for cline-free/mimo-v2.6-flash was reached ('daily free model limit'); resets in about 19h 17m (~2026-09-25T20:37:01Z). Quota, not a model failure; does not count against the row's attempts.", "cost_usd": null, "cost_basis": "unknown", "usage_not_reported": true, "status": "infra_dnf", "failure_class": "QUOTA" }, { "id": "fjord__raw-api__opus-5-5__max__attempt3", "cell": "fjord__raw-api__opus-5-5__max", "attempt": 3, "result_id": "fjord__raw-api__opus-5-5__max__attempt6", "prompt_id": "fjord", "model": "Claude Opus 5.5", "model_id": "claude-opus-5-5", "harness": "none (raw API)", "harness_family": "none (raw API)", "track": "raw_baseline", "effort": "max", "run_date": "2026-09-25", "started_utc": "2026-09-25T01:33:36Z", "wall_time_s": 15.3, "note": "The connection upstream of the harness dropped the run (API Error: 502