Versioned benchmark collection

Neon Gunner

Public ledger · prompt hash recorded · 15 measured runs across 1 target. Each entry is a single recorded attempt; repeat-run reliability is not established.

Neon Gunner public evidence
Neon Gunner public evidence
15Measured runs
1Frozen targets
14Model families
15Configurations
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

  • Neon Gunner

Model coverage

  • DeepSeek V4 Flash · Max
  • DeepSeek V4 Flash · Vision exp
  • DeepSeek V4.1 Flash · Highest
  • Claude Fable 5.1 · Max
  • Gemini 3.8 Flash · Highest
  • GLM 5.3 Flash · Max
  • GPT-5.6 Luna · Max
  • GPT-6 Astra · Max
  • GPT-6 Sol · Max
  • Grok 4.6 · xhigh
  • Kimi K3 · Max
  • MiMo V2.6 Pro · Unreported
  • Claude Opus 5.5 · Max
  • Qwen3.8 Flash · Unreported
  • DeepSeek V4 Pro · Max

Evidence available

  • 15 runs on prompt 9e2402337e53
  • Prompt SHA-256 9e2402337e536af36e200f63f0cbe30579d9e6d947170b01d394c077f80069dc
  • 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.
  • 3 related records are listed separately and are not attached to this prompt.
  • Repeat-run reliability evidence is not established.
Public receipts

15 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 · Neon Gunnerpartial_metrics_and_validator_ledger · 26/26 checks recorded · Prompt version v1$0.20 OpenCode Go API-equivalent usage accounting, not an itemized subscription cash chargerecorded estimate5h 9m 39.389s wall-clockEnd-to-end workflowOpen 02DeepSeek V4 FlashVision exp reasoning · Neon GunnerPARTIAL · Prompt version unreported$0.54 Provider-recorded OpenRouter costrecorded estimateNot recordedEnd-to-end workflowOpen 03DeepSeek V4.1 FlashHighest reasoning · Neon Gunnercomplete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreported$0.34 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate3224.4s wall-clockEnd-to-end workflowOpen 04Claude Fable 5.1Max reasoning · Neon Gunnerpartial_active_session_snapshot_with_supplied_validation · PARTIAL_PASS · Prompt version v1$95.09 Official Anthropic API-list-price equivalent from the supplied active-session snapshot, not an itemized Claude Code subscription charge.recorded estimate55m 21.3s wall-clockEnd-to-end workflowOpen 05Gemini 3.8 FlashHighest reasoning · Neon Gunnercomplete_token_timing_artifact_and_validation_ledger · pass_with_nonbenchmark_caveat · Prompt version unreported$2.59 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate1463.9s wall-clockEnd-to-end workflowOpen 06GLM 5.3 FlashMax reasoning · Neon GunnerPENDING_JUDGE · Prompt version unreported$0.79 Provider-recorded OpenRouter costrecorded estimate3h 9m 20.539s wall-clockEnd-to-end workflowOpen 07GPT-5.6 LunaMax reasoning · Neon GunnerPASS · Prompt version unreportedNot recordedrecorded estimateNot recordedEnd-to-end workflowOpen 08GPT-6 AstraMax reasoning · Neon Gunnerpartial_post_task_metrics_snapshot_with_supplied_validation · Prompt version v1$9.90 API-equivalent estimate from a qualified post-task snapshot, not a subscription invoicerecorded estimate44m 55.2s (supplemental snapshot span) wall-clockEnd-to-end workflowOpen 09GPT-6 SolMax reasoning · Neon Gunnercomplete_token_timing_artifact_and_validation_ledger · Prompt version unreported$3.86 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 10Grok 4.6xhigh reasoning · Neon Gunnerpartial_multi_user_turn_metrics_artifact_and_supplied_validator_ledger · PASS · Prompt version v1$6.73 Provider-recorded usage estimate, not a subscription cash-charge invoicerecorded estimate32m 15.261s wall-clockEnd-to-end workflowOpen 11Kimi K3Max reasoning · Neon Gunnerpartial_quota_interrupted_model_runtime_verified · RUNTIME_PASS_MODEL_QUOTA_INTERRUPTED · Prompt version v1Not recordedrecorded estimate5378.1s wall-clockEnd-to-end workflowOpen 12MiMo V2.6 ProUnreported reasoning · Neon Gunnercomplete_by_contestant_internal_verdict_metrics_method_partial · Prompt version unreported$0.85 API-equivalent list price, not a marginal subscription cash chargerecorded estimate4671.3s wall-clockEnd-to-end workflowOpen 13Claude Opus 5.5Max reasoning · Neon Gunnercomplete · Prompt version v1$33.38 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 14Qwen3.8 FlashUnreported reasoning · Neon GunnerPARTIAL · Prompt version unreported$0.79 Provider-recorded OpenRouter costrecorded estimate1h 39m 59.195s wall-clockEnd-to-end workflowOpen 15DeepSeek V4 ProMax reasoning · Neon Gunnercomplete_token_timing_artifact_and_validation_ledger · 26/26 pass, zero console errors · Prompt version unreported$0.29 API-equivalent accountingrecorded estimate1h 41m 9.8s 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.

neon-gunner-canvas

SHA-256 9e2402337e536af36e200f63f0cbe30579d9e6d947170b01d394c077f80069dc

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.