jrpg-boss-battle-threejs
SHA-256 fff411e987052ac2f06a5027f5ea596171af9cfb9ddde67524462dca01519f96
Path benchmarks/prompts/jrpg-boss-battle-threejs.v1.md
Versioned benchmark collection
JRPG Boss Battle v1
Harness v1 · 22 measured runs across 1 target. Each entry is a single recorded attempt; repeat-run reliability is not established.
22Measured runs
1Frozen targets
19Model families
20Configurations
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
- JRPG boss battle
Model coverage
- DeepSeek V4 Flash · Max
- DeepSeek V4 Pro · Max
- Claude Fable 5 · Max
- Claude Fable 5.1 · Max
- GPT-5.6 Luna · Max
- GPT-5.6 Sol · Ultra
- GPT-6 Astra · Max
- GPT-6 Sol · Max
- Grok 4.6 · xhigh
- Kimi K3 · Max
- MiMo V2.6 Pro · High
- Claude Opus 5 · Max
- Claude Opus 5.5 · High
- Qwen3.8 Max Preview · Mandatory thinking enabled
- Qwen3.8 Max · xhigh
- DeepSeek V4 Flash · Vision exp
- DeepSeek V4.1 Flash · Highest
- Gemini 3.8 Flash · Highest
- GLM 5.3 Flash · Max
- Qwen3.8 Flash · Unreported
Evidence available
- 22 measured run ledgers
- Public recorded outputs
- Cost, token, and workflow timing
- Prompt SHA-256 fff411e987052ac2f06a5027f5ea596171af9cfb9ddde67524462dca01519f96
- Recorded prompt path benchmarks/prompts/jrpg-boss-battle-threejs.v1.md
Still missing
- Repeat-run reliability evidence
- Minimum blind-vote sample
- 3 related records are listed separately and are not attached to this prompt.
Public receipts
22 measured run ledgers
Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.
01DeepSeek V4 FlashMax reasoning · JRPG boss battlepartial_token_timing_artifact_validation_ledger · Prompt version v1$0.07 API-equivalent usage accounting, not an itemized subscription cash chargerecorded estimate32m 0.3s wall-clockEnd-to-end workflowOpen 02DeepSeek V4 ProMax reasoning · JRPG boss battlecomplete_token_timing_artifact_and_independent_validation_ledger · Prompt version v1$0.13 API-equivalent accounting, not itemized subscription cashrecorded estimate45m 51.8s wall-clockEnd-to-end workflowOpen 03Claude Fable 5Max reasoning · JRPG boss battlepartial_token_timing_artifact_validation_ledger · PASS, 41/41 checks · Prompt version v1$123.42 API-equivalent estimate with exact cache-write TTL accounting, not a subscription invoicerecorded estimate50:48.1 wall-clockEnd-to-end workflowOpen 04Claude Fable 5.1Max reasoning · JRPG boss battlepartial_token_timing_artifact_validation_ledger_with_independent_replay · Prompt version v1$108.88 API-equivalent estimate with 1-hour cache-write pricing, not a subscription invoicerecorded estimate5h 27m 19s wall-clockEnd-to-end workflowOpen 05GPT-5.6 LunaMax reasoning · JRPG boss battlepartial_token_timing_artifact_validation_ledger · PASS, 41/41 checks · Prompt version v1$0.27 API-equivalent estimate, not a subscription invoicerecorded estimate26m 52.2s wall-clockEnd-to-end workflowOpen 06GPT-5.6 SolUltra reasoning · JRPG boss battlepartial_token_timing_artifact_validation_ledger · PASS, 41/41 checks · Prompt version v1$9.98 API-equivalent estimate, not a subscription invoicerecorded estimate25:51.8 wall-clockEnd-to-end workflowOpen 07GPT-6 AstraMax reasoning · JRPG boss battlepartial_completed_run_metrics_with_live_operator_smoke · Prompt version v1$12.65 API-equivalent estimate, not a subscription invoicerecorded estimate34m 22s wall-clockEnd-to-end workflowOpen 08GPT-6 SolMax reasoning · JRPG boss battlecomplete_token_timing_artifact_and_validation_ledger · Prompt version unreported$1.39 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 09Grok 4.6xhigh reasoning · JRPG boss battlepartial_one_shot_token_timing_artifact_validation_ledger · Prompt version v1$3.08 Provider-recorded usage estimate, not a subscription cash-charge invoicerecorded estimate19m 35.680s wall-clockEnd-to-end workflowOpen 10Kimi K3Max reasoning · JRPG boss battlepartial_token_timing_artifact_validation_ledger · PASS, 41/41 checks · Prompt version v1$2.86 API-equivalent usage accounting, not an itemized subscription cash chargerecorded estimate41:20.2 wall-clockEnd-to-end workflowOpen 11MiMo V2.6 ProHigh reasoning · JRPG boss battlepartial · Prompt version v1$0.31 live OpenCode OpenRouter model entry and exact one-turn session usage ledgerrecorded estimate1782.6s wall-clockEnd-to-end workflowOpen 12MiMo V2.6 ProHigh reasoning · JRPG boss battlepartial · Prompt version v1$0.16 live OpenCode OpenRouter model entry and bounded same-session usage extractorrecorded estimate1562.4s wall-clockEnd-to-end workflowOpen 13Claude Opus 5Max reasoning · JRPG boss battlepartial_token_timing_artifact_validation_ledger · PASS, 41/41 checks · Prompt version v1$48.95 First-party Claude API list-price equivalent, not a Claude Code subscription invoicerecorded estimate1h 15m 49.9s wall-clockEnd-to-end workflowOpen 14Claude Opus 5.5High reasoning · JRPG boss battlecomplete · Prompt version v1$6.17 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 15Qwen3.8 Max PreviewMandatory thinking enabled reasoning · JRPG boss battlepublished_artifact_validation_runtime_ledger · PASS · Prompt version v1$15.15 Qualified third-party NanoGPT API-list-price scenario for the measured token mix; not an Alibaba Token Plan cash chargerecorded estimate58m 40.6s wall-clockEnd-to-end workflowOpen 16Qwen3.8 Maxxhigh reasoning · JRPG boss battlepublished_artifact_validator_runtime_ledger_partial_metrics · PASS — 41/41 · Prompt version v1¥43.72 Independently recomputed first-party API-list-price equivalent for the measured token mix; NOT a billed amount. This run used an Alibaba Model Studio token-plan subscription, under which usage is not itemized as cash.recorded estimate1h 42m 47.5s wall-clockEnd-to-end workflowOpen 17DeepSeek V4 FlashVision exp reasoning · JRPG boss battlePASS · Prompt version unreported$0.23 Provider-recorded OpenRouter costrecorded estimateNot recordedEnd-to-end workflowOpen 18DeepSeek V4.1 FlashHighest reasoning · JRPG boss battlecomplete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreported$0.16 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate2046.7s wall-clockEnd-to-end workflowOpen 19Gemini 3.8 FlashHighest reasoning · JRPG boss battlecomplete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreported$1.12 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate1530.7s wall-clockEnd-to-end workflowOpen 20GLM 5.3 FlashMax reasoning · JRPG boss battlePARTIAL · Prompt version unreported$0.16 Provider-recorded OpenRouter costrecorded estimate52m 42.980s wall-clockEnd-to-end workflowOpen 21GPT-5.6 LunaMax reasoning · JRPG boss battlePENDING_JUDGE · Prompt version unreportedNot recordedrecorded estimateNot recordedEnd-to-end workflowOpen 22Qwen3.8 FlashUnreported reasoning · JRPG boss battlePENDING_JUDGE · Prompt version unreported$0.14 Provider-recorded OpenRouter costrecorded estimate36m 43.822s 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.
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.
Limits
Evidence and material gaps
- Repeat-run reliability evidence is not established.