BuilderBuilder
Versioned benchmark collection

Apple stem

Public ledger · prompt hash recorded · 12 measured runs across 1 target. Each entry is a single recorded attempt; repeat-run reliability is not established.

Inspect the run ledgers← All collections
Apple stem public evidence
Apple stem public evidence
12Measured runs
1Frozen targets
11Model families
12Configurations
Collection scope

Recorded evidence, without a synthetic score.

Runs share the same frozen target and prompt within each test, with disclosed provider-specific stacks. Costs are recorded estimates as labelled in each ledger, not subscription invoices.

Targets

  • Apple Stem

Model coverage

  • DeepSeek V4.1 Flash · Highest
  • Gemini 3.8 Flash · High
  • GLM 5.3 Flash · Highest
  • GPT-6 Astra · Low
  • GPT-6 Astra · Max
  • GPT-6 Sol · Max
  • Grok 4.6 · xhigh
  • Grok 4.7 · xhigh
  • MiMo V2.6 Pro · Highest
  • Claude Opus 5 · Max
  • Claude Opus 5.5 · Max
  • Qwen3.8 Flash · Highest

Evidence available

  • 12 runs on prompt b3577f3b5c8e
  • Prompt SHA-256 b3577f3b5c8e77886df895d6e7846fad2fa8642440eea9db11a099e3ea7b2038
  • Exact prompt file path was not published

Still missing

  • No released Builder project, harness package, or skill download.
  • Exact prompt file path was not published with this test.
  • 7 related records are listed separately and are not attached to this prompt.
  • Repeat-run reliability evidence is not established.
Public receipts

12 measured run ledgers

Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.

01DeepSeek V4.1 FlashHighest reasoning · Apple Stemjudge_fail_independently_replayed · pass · Prompt version v1$0.10 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate88m 20.2s wall-clockEnd-to-end workflowOpen 02Gemini 3.8 FlashHigh reasoning · Apple Stemjudge_fail_independently_replayed · pass · Prompt version v1$5.39 API-equivalent list price, not a marginal subscription cash chargerecorded estimate69m 1s wall-clockEnd-to-end workflowOpen 03GLM 5.3 FlashHighest reasoning · Apple Stemjudge_pass_independently_replayed · pass · Prompt version v1$0.56 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate89m 33.2s wall-clockEnd-to-end workflowOpen 04GPT-6 AstraLow reasoning · Apple Stemjudge_pass_independently_replayed · PASS · Prompt version v1$4.98 Standard API-equivalent estimate from the Codex wrapper receipt, not a subscription invoice: this was a ChatGPT-subscription run, $0 was charged and Codex emits no cost field.recorded estimate18m 09s wall-clockEnd-to-end workflowOpen 05GPT-6 AstraMax reasoning · Apple Stemjudge_pass_independently_replayed · PASS · Prompt version v1$3.48 Standard API-equivalent estimate from the Codex wrapper receipt, not a subscription invoice: this was a ChatGPT-subscription run, $0 was charged and Codex emits no cost field.recorded estimate11m 05s wall-clockEnd-to-end workflowOpen 06GPT-6 SolMax reasoning · Apple Stemjudge_pass_independently_replayed · PASS · Prompt version v1$1.08 Standard API-equivalent estimate from the Codex wrapper receipt, not a subscription invoice: this was a ChatGPT-subscription run, $0 was charged and Codex emits no cost field.recorded estimate28m 08s wall-clockEnd-to-end workflowOpen 07Grok 4.6xhigh reasoning · Apple Stemjudge_pass_independently_replayed · PASS · Prompt version v1Not recordedrecorded estimate1h 30m 00s wrapper wall (submission written at 51m 21s) wall-clockEnd-to-end workflowOpen 08Grok 4.7xhigh reasoning · Apple Stemjudge_fail_independently_replayed · PASS · Prompt version v1$5.18 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate118m 14s wall-clockEnd-to-end workflowOpen 09MiMo V2.6 ProHighest reasoning · Apple Stemjudge_pass_independently_replayed · pass · Prompt version v1$0.32 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate104m 01.5s wall-clockEnd-to-end workflowOpen 10Claude Opus 5Max reasoning · Apple Stemjudge_pass_independently_replayed · PASS · Prompt version v1$7.70 API-equivalent estimate from session token counts at Anthropic list price (input $5, output $25, cache read $0.50, cache write $6.25 per MTok)recorded estimate33m 30s wall-clockEnd-to-end workflowOpen 11Claude Opus 5.5Max reasoning · Apple Stemjudge_pass_independently_replayed · PASS · Prompt version v1$2.11 recorded total_cost_usd from workspace FINAL.json (modelUsage.claude-opus-5-5, costBasis=list, Anthropic list price). Charged to the Claude subscription ($0 charged).recorded estimate16m 39s wall-clockEnd-to-end workflowOpen 12Qwen3.8 FlashHighest reasoning · Apple Stemfailed_no_submission · pass · Prompt version v1$0.24 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate88m 21.1s wall-clockEnd-to-end workflowOpen
Prompt provenance

Exact prompt receipts

A path is shown only when the published record includes the prompt hash that identifies it. Campaign evidence and projections keep the hash gap visible.

dex-apple-stem-superdex

SHA-256 b3577f3b5c8e77886df895d6e7846fad2fa8642440eea9db11a099e3ea7b2038

Exact prompt file path was not published.

Separate records

Related records with unknown prompt provenance

These published records stay separate from the prompt receipts above. Unknown provenance is why they are listed here.