Verimium

yambda-discovery-ranking-basic

Build a leakage-safe music-discovery ranker within a fixed CPU and time budget.

Task Description

Inputs: Chronological listen and preference events, target users, cutoff-correct candidate sets, explicit preference state, and a public temporal backtest. No starter model is supplied.

Task: Design, tune, and refit a ranker that returns 100 eligible tracks for every target user. Any modeling approach is allowed inside the platform-owned candidate boundary. The agent has 30 min on 4 CPU · 8 GB · no GPU.

Verification: The offline verifier validates the ranking artifact and scores it on a hidden seven-day outcome window using graded NDCG@10. A run passes at NDCG@10 ≥ 0.025.

Results

55 qualified runs

Individual attempts

Rewards by model, harness, and reasoning effort for yambda-discovery-ranking-v01 opus-5.0 Claude Code v2.1.251 High effort opus-5.5 Claude Code v2.1.283 High effort Fable 5.1 Claude Code v2.1.288 High effort gpt-5.6-sol Codex v0.147.0 High effort Grok 4.6 Grok Build v1.0.44 High effort gpt-5.6-sol Codex v0.153.4 High effort gpt-6-astra Codex v0.153.4 High effort gpt-5.6-sol Codex v0.153.4 Medium effort gpt-5.6-sol Codex v0.153.4 Max effort Gemini 3.8 Flash Gemini CLI v0.61.0 High effort opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-5. Reward: 0.009092.. Agent time: 30m 2s. Recorded steps: 48yambda-opus-high-2026-09-24-00-34-15-04330cf-5: 0.009092. Agent time: 30m 2s. Recorded steps: 48 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-2. Reward: 0.020738.. Agent time: 13m 39s. Recorded steps: 27yambda-opus-high-2026-09-24-00-34-15-04330cf-2: 0.020738. Agent time: 13m 39s. Recorded steps: 27 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-1. Reward: 0.021172.. Agent time: 7m 50s. Recorded steps: 16yambda-opus-high-2026-09-24-00-34-15-04330cf-1: 0.021172. Agent time: 7m 50s. Recorded steps: 16 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-4. Reward: 0.026023.. Agent time: 10m 30s. Recorded steps: 24yambda-opus-high-2026-09-24-00-34-15-04330cf-4: 0.026023. Agent time: 10m 30s. Recorded steps: 24 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-3. Reward: 0.030378.. Agent time: 20m 35s. Recorded steps: 23yambda-opus-high-2026-09-24-00-34-15-04330cf-3: 0.030378. Agent time: 20m 35s. Recorded steps: 23 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r04-20260926T034923Z. Reward: 0.022903.. Agent time: 18m 0s. Recorded steps: 20opus55-high-2-1-283-basic-r04-20260926T034923Z: 0.022903. Agent time: 18m 0s. Recorded steps: 20 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r05-20260926T034923Z. Reward: 0.032805.. Agent time: 8m 28s. Recorded steps: 16opus55-high-2-1-283-basic-r05-20260926T034923Z: 0.032805. Agent time: 8m 28s. Recorded steps: 16 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r03-20260926T034923Z. Reward: 0.032849.. Agent time: 6m 2s. Recorded steps: 14opus55-high-2-1-283-basic-r03-20260926T034923Z: 0.032849. Agent time: 6m 2s. Recorded steps: 14 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r01-20260926T034923Z. Reward: 0.033498.. Agent time: 5m 59s. Recorded steps: 17opus55-high-2-1-283-basic-r01-20260926T034923Z: 0.033498. Agent time: 5m 59s. Recorded steps: 17 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r02-20260926T034923Z-retry1. Reward: 0.038827.. Agent time: 7m 46s. Recorded steps: 13opus55-high-2-1-283-basic-r02-20260926T034923Z-retry1: 0.038827. Agent time: 7m 46s. Recorded steps: 13 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r05-20261003T075109Z. Reward: 0.021079.. Agent time: 15m 25s. Recorded steps: 17fable51-high-2-1-288-basic-r05-20261003T075109Z: 0.021079. Agent time: 15m 25s. Recorded steps: 17 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r03-20261003T075109Z. Reward: 0.030161.. Agent time: 13m 28s. Recorded steps: 18fable51-high-2-1-288-basic-r03-20261003T075109Z: 0.030161. Agent time: 13m 28s. Recorded steps: 18 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r02-20261003T075109Z-queued. Reward: 0.031604.. Agent time: 14m 35s. Recorded steps: 18fable51-high-2-1-288-basic-r02-20261003T075109Z-queued: 0.031604. Agent time: 14m 35s. Recorded steps: 18 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r04-20261003T075109Z. Reward: 0.033316.. Agent time: 9m 15s. Recorded steps: 15fable51-high-2-1-288-basic-r04-20261003T075109Z: 0.033316. Agent time: 9m 15s. Recorded steps: 15 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r01-20261003T072422Z. Reward: 0.034059.. Agent time: 11m 19s. Recorded steps: 16fable51-high-2-1-288-basic-r01-20261003T072422Z: 0.034059. Agent time: 11m 19s. Recorded steps: 16 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r01-2026-09-24. Reward: 0.000000 (assigned). Validation failed: missing submission.parquet or submission.csv. Agent time: 30m 3s. Recorded steps: 67sol-high-0.147.0-exact-r01-2026-09-24: 0.000000 (assigned zero: no valid artifact or verifier reward). Agent time: 30m 3s. Recorded steps: 67 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r02-2026-09-24. Reward: 0.026471.. Agent time: 27m 52s. Recorded steps: 87sol-high-0.147.0-exact-r02-2026-09-24: 0.026471. Agent time: 27m 52s. Recorded steps: 87 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r05-2026-09-24. Reward: 0.030634.. Agent time: 29m 53s. Recorded steps: 92sol-high-0.147.0-exact-r05-2026-09-24: 0.030634. Agent time: 29m 53s. Recorded steps: 92 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r03-2026-09-24. Reward: 0.032421.. Agent time: 20m 50s. Recorded steps: 69sol-high-0.147.0-exact-r03-2026-09-24: 0.032421. Agent time: 20m 50s. Recorded steps: 69 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r04-2026-09-24. Reward: 0.033728.. Agent time: 30m 3s. Recorded steps: 79sol-high-0.147.0-exact-r04-2026-09-24: 0.033728. Agent time: 30m 3s. Recorded steps: 79 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r01-61e7dce0-20260929. Reward: 0.008780.. Agent time: 30m 3s. Recorded steps: 30grok-1-0-44-basic-r01-61e7dce0-20260929: 0.008780. Agent time: 30m 3s. Recorded steps: 30 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r04-61e7dce0-20260929. Reward: 0.008780.. Agent time: 30m 3s. Recorded steps: 25grok-1-0-44-basic-r04-61e7dce0-20260929: 0.008780. Agent time: 30m 3s. Recorded steps: 25 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r05-61e7dce0-20260929. Reward: 0.008780.. Agent time: 30m 3s. Recorded steps: 58grok-1-0-44-basic-r05-61e7dce0-20260929: 0.008780. Agent time: 30m 3s. Recorded steps: 58 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r03-61e7dce0-20260929. Reward: 0.009092.. Agent time: 30m 2s. Recorded steps: 34grok-1-0-44-basic-r03-61e7dce0-20260929: 0.009092. Agent time: 30m 2s. Recorded steps: 34 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r02-61e7dce0-20260929. Reward: 0.030785.. Agent time: 30m 3s. Recorded steps: 35grok-1-0-44-basic-r02-61e7dce0-20260929: 0.030785. Agent time: 30m 3s. Recorded steps: 35 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r04-recovery-20260923T212844Z. Reward: 0.000000 (assigned). Validation failed: missing submission.parquet or submission.csv. Agent time: 30m 3s. Recorded steps: 75base-sol-high-cli-0-153-4-r04-recovery-20260923T212844Z: 0.000000 (assigned zero: no valid artifact or verifier reward). Agent time: 30m 3s. Recorded steps: 75 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r03-recovery-20260923T212844Z. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 74base-sol-high-cli-0-153-4-r03-recovery-20260923T212844Z: 0.009092. Agent time: 30m 3s. Recorded steps: 74 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r01-recovery-20260923T212844Z. Reward: 0.024660.. Agent time: 28m 5s. Recorded steps: 80base-sol-high-cli-0-153-4-r01-recovery-20260923T212844Z: 0.024660. Agent time: 28m 5s. Recorded steps: 80 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r02-recovery-20260923T212844Z. Reward: 0.025398.. Agent time: 30m 3s. Recorded steps: 69base-sol-high-cli-0-153-4-r02-recovery-20260923T212844Z: 0.025398. Agent time: 30m 3s. Recorded steps: 69 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r05-recovery-20260923T212844Z. Reward: 0.028513.. Agent time: 30m 3s. Recorded steps: 70base-sol-high-cli-0-153-4-r05-recovery-20260923T212844Z: 0.028513. Agent time: 30m 3s. Recorded steps: 70 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r01-20260923T050949Z. Reward: 0.042554.. Agent time: 29m 25s. Recorded steps: 80base-astra-high-cli-0-153-4-r01-20260923T050949Z: 0.042554. Agent time: 29m 25s. Recorded steps: 80 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r02-20260923T050949Z. Reward: 0.046185.. Agent time: 28m 22s. Recorded steps: 100base-astra-high-cli-0-153-4-r02-20260923T050949Z: 0.046185. Agent time: 28m 22s. Recorded steps: 100 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r05-20260923T050949Z. Reward: 0.048050.. Agent time: 29m 17s. Recorded steps: 91base-astra-high-cli-0-153-4-r05-20260923T050949Z: 0.048050. Agent time: 29m 17s. Recorded steps: 91 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r04-20260923T050949Z. Reward: 0.049333.. Agent time: 29m 23s. Recorded steps: 97base-astra-high-cli-0-153-4-r04-20260923T050949Z: 0.049333. Agent time: 29m 23s. Recorded steps: 97 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r03-20260923T050949Z. Reward: 0.049784.. Agent time: 26m 56s. Recorded steps: 92base-astra-high-cli-0-153-4-r03-20260923T050949Z: 0.049784. Agent time: 26m 56s. Recorded steps: 92 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r04-20260924T221413Z. Reward: 0.019697.. Agent time: 11m 43s. Recorded steps: 39sol-medium-0-153-4-basic-r04-20260924T221413Z: 0.019697. Agent time: 11m 43s. Recorded steps: 39 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r03-20260924T221413Z. Reward: 0.026425.. Agent time: 24m 33s. Recorded steps: 47sol-medium-0-153-4-basic-r03-20260924T221413Z: 0.026425. Agent time: 24m 33s. Recorded steps: 47 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r01-20260924T221413Z. Reward: 0.027901.. Agent time: 13m 59s. Recorded steps: 41sol-medium-0-153-4-basic-r01-20260924T221413Z: 0.027901. Agent time: 13m 59s. Recorded steps: 41 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r05-20260924T221413Z. Reward: 0.034125.. Agent time: 11m 52s. Recorded steps: 39sol-medium-0-153-4-basic-r05-20260924T221413Z: 0.034125. Agent time: 11m 52s. Recorded steps: 39 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r02-20260924T221413Z. Reward: 0.035517.. Agent time: 16m 34s. Recorded steps: 40sol-medium-0-153-4-basic-r02-20260924T221413Z: 0.035517. Agent time: 16m 34s. Recorded steps: 40 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r01-20260924T221413Z-retry01. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 117sol-max-0-153-4-basic-r01-20260924T221413Z-retry01: 0.009092. Agent time: 30m 3s. Recorded steps: 117 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r05-20260924T221413Z. Reward: 0.009092.. Agent time: 30m 2s. Recorded steps: 74sol-max-0-153-4-basic-r05-20260924T221413Z: 0.009092. Agent time: 30m 2s. Recorded steps: 74 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r02-20260924T221413Z. Reward: 0.035815.. Agent time: 30m 3s. Recorded steps: 82sol-max-0-153-4-basic-r02-20260924T221413Z: 0.035815. Agent time: 30m 3s. Recorded steps: 82 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r03-20260924T221413Z. Reward: 0.037559.. Agent time: 24m 39s. Recorded steps: 100sol-max-0-153-4-basic-r03-20260924T221413Z: 0.037559. Agent time: 24m 39s. Recorded steps: 100 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r04-20260924T221413Z. Reward: 0.039252.. Agent time: 28m 9s. Recorded steps: 156sol-max-0-153-4-basic-r04-20260924T221413Z: 0.039252. Agent time: 28m 9s. Recorded steps: 156 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r05-3d6fca60. Reward: 0.009070.. Agent time: 30m 3s. Recorded steps: 63gemini-3-8-flash-high-basic-fixed-r05-3d6fca60: 0.009070. Agent time: 30m 3s. Recorded steps: 63 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r01-d0433654. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 56gemini-3-8-flash-high-basic-fixed-r01-d0433654: 0.009092. Agent time: 30m 3s. Recorded steps: 56 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r02-d237f45e. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 41gemini-3-8-flash-high-basic-fixed-r02-d237f45e: 0.009092. Agent time: 30m 3s. Recorded steps: 41 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r03-d237f45e. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 51gemini-3-8-flash-high-basic-fixed-r03-d237f45e: 0.009092. Agent time: 30m 3s. Recorded steps: 51 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r04-d237f45e. Reward: 0.009092.. Agent time: 30m 5s. Recorded steps: 54gemini-3-8-flash-high-basic-fixed-r04-d237f45e: 0.009092. Agent time: 30m 5s. Recorded steps: 54 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r01-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 69gemini-3-8-flash-high-basic-r01-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 69 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r02-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 50gemini-3-8-flash-high-basic-r02-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 50 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r04-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 58gemini-3-8-flash-high-basic-r04-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 58 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r05-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 56gemini-3-8-flash-high-basic-r05-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 56 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r03-b9049e57. Reward: 0.009112.. Agent time: 30m 3s. Recorded steps: 60gemini-3-8-flash-high-basic-r03-b9049e57: 0.009112. Agent time: 30m 3s. Recorded steps: 60 0.00 0.01 0.02 0.03 0.04 0.05 Hidden NDCG@10 · Higher is better
Rewards by model, harness, and reasoning effort for yambda-discovery-ranking-v01 opus-5.0 Claude Code v2.1.251 High effort opus-5.5 Claude Code v2.1.283 High effort Fable 5.1 Claude Code v2.1.288 High effort gpt-5.6-sol Codex v0.147.0 High effort Grok 4.6 Grok Build v1.0.44 High effort gpt-5.6-sol Codex v0.153.4 High effort gpt-6-astra Codex v0.153.4 High effort gpt-5.6-sol Codex v0.153.4 Medium effort gpt-5.6-sol Codex v0.153.4 Max effort Gemini 3.8 Flash Gemini CLI v0.61.0 High effort opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-5. Reward: 0.009092.. Agent time: 30m 2s. Recorded steps: 48yambda-opus-high-2026-09-24-00-34-15-04330cf-5: 0.009092. Agent time: 30m 2s. Recorded steps: 48 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-2. Reward: 0.020738.. Agent time: 13m 39s. Recorded steps: 27yambda-opus-high-2026-09-24-00-34-15-04330cf-2: 0.020738. Agent time: 13m 39s. Recorded steps: 27 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-1. Reward: 0.021172.. Agent time: 7m 50s. Recorded steps: 16yambda-opus-high-2026-09-24-00-34-15-04330cf-1: 0.021172. Agent time: 7m 50s. Recorded steps: 16 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-4. Reward: 0.026023.. Agent time: 10m 30s. Recorded steps: 24yambda-opus-high-2026-09-24-00-34-15-04330cf-4: 0.026023. Agent time: 10m 30s. Recorded steps: 24 opus-5.0 / Claude Code v2.1.251 · high effort · yambda-opus-high-2026-09-24-00-34-15-04330cf-3. Reward: 0.030378.. Agent time: 20m 35s. Recorded steps: 23yambda-opus-high-2026-09-24-00-34-15-04330cf-3: 0.030378. Agent time: 20m 35s. Recorded steps: 23 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r04-20260926T034923Z. Reward: 0.022903.. Agent time: 18m 0s. Recorded steps: 20opus55-high-2-1-283-basic-r04-20260926T034923Z: 0.022903. Agent time: 18m 0s. Recorded steps: 20 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r05-20260926T034923Z. Reward: 0.032805.. Agent time: 8m 28s. Recorded steps: 16opus55-high-2-1-283-basic-r05-20260926T034923Z: 0.032805. Agent time: 8m 28s. Recorded steps: 16 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r03-20260926T034923Z. Reward: 0.032849.. Agent time: 6m 2s. Recorded steps: 14opus55-high-2-1-283-basic-r03-20260926T034923Z: 0.032849. Agent time: 6m 2s. Recorded steps: 14 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r01-20260926T034923Z. Reward: 0.033498.. Agent time: 5m 59s. Recorded steps: 17opus55-high-2-1-283-basic-r01-20260926T034923Z: 0.033498. Agent time: 5m 59s. Recorded steps: 17 opus-5.5 / Claude Code v2.1.283 · high effort · opus55-high-2-1-283-basic-r02-20260926T034923Z-retry1. Reward: 0.038827.. Agent time: 7m 46s. Recorded steps: 13opus55-high-2-1-283-basic-r02-20260926T034923Z-retry1: 0.038827. Agent time: 7m 46s. Recorded steps: 13 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r05-20261003T075109Z. Reward: 0.021079.. Agent time: 15m 25s. Recorded steps: 17fable51-high-2-1-288-basic-r05-20261003T075109Z: 0.021079. Agent time: 15m 25s. Recorded steps: 17 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r03-20261003T075109Z. Reward: 0.030161.. Agent time: 13m 28s. Recorded steps: 18fable51-high-2-1-288-basic-r03-20261003T075109Z: 0.030161. Agent time: 13m 28s. Recorded steps: 18 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r02-20261003T075109Z-queued. Reward: 0.031604.. Agent time: 14m 35s. Recorded steps: 18fable51-high-2-1-288-basic-r02-20261003T075109Z-queued: 0.031604. Agent time: 14m 35s. Recorded steps: 18 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r04-20261003T075109Z. Reward: 0.033316.. Agent time: 9m 15s. Recorded steps: 15fable51-high-2-1-288-basic-r04-20261003T075109Z: 0.033316. Agent time: 9m 15s. Recorded steps: 15 fable-5.1 / Claude Code v2.1.288 · high effort · fable51-high-2-1-288-basic-r01-20261003T072422Z. Reward: 0.034059.. Agent time: 11m 19s. Recorded steps: 16fable51-high-2-1-288-basic-r01-20261003T072422Z: 0.034059. Agent time: 11m 19s. Recorded steps: 16 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r01-2026-09-24. Reward: 0.000000 (assigned). Validation failed: missing submission.parquet or submission.csv. Agent time: 30m 3s. Recorded steps: 67sol-high-0.147.0-exact-r01-2026-09-24: 0.000000 (assigned zero: no valid artifact or verifier reward). Agent time: 30m 3s. Recorded steps: 67 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r02-2026-09-24. Reward: 0.026471.. Agent time: 27m 52s. Recorded steps: 87sol-high-0.147.0-exact-r02-2026-09-24: 0.026471. Agent time: 27m 52s. Recorded steps: 87 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r05-2026-09-24. Reward: 0.030634.. Agent time: 29m 53s. Recorded steps: 92sol-high-0.147.0-exact-r05-2026-09-24: 0.030634. Agent time: 29m 53s. Recorded steps: 92 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r03-2026-09-24. Reward: 0.032421.. Agent time: 20m 50s. Recorded steps: 69sol-high-0.147.0-exact-r03-2026-09-24: 0.032421. Agent time: 20m 50s. Recorded steps: 69 gpt-5.6-sol / Codex v0.147.0 · high effort · sol-high-0.147.0-exact-r04-2026-09-24. Reward: 0.033728.. Agent time: 30m 3s. Recorded steps: 79sol-high-0.147.0-exact-r04-2026-09-24: 0.033728. Agent time: 30m 3s. Recorded steps: 79 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r01-61e7dce0-20260929. Reward: 0.008780.. Agent time: 30m 3s. Recorded steps: 30grok-1-0-44-basic-r01-61e7dce0-20260929: 0.008780. Agent time: 30m 3s. Recorded steps: 30 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r04-61e7dce0-20260929. Reward: 0.008780.. Agent time: 30m 3s. Recorded steps: 25grok-1-0-44-basic-r04-61e7dce0-20260929: 0.008780. Agent time: 30m 3s. Recorded steps: 25 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r05-61e7dce0-20260929. Reward: 0.008780.. Agent time: 30m 3s. Recorded steps: 58grok-1-0-44-basic-r05-61e7dce0-20260929: 0.008780. Agent time: 30m 3s. Recorded steps: 58 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r03-61e7dce0-20260929. Reward: 0.009092.. Agent time: 30m 2s. Recorded steps: 34grok-1-0-44-basic-r03-61e7dce0-20260929: 0.009092. Agent time: 30m 2s. Recorded steps: 34 grok-4.6 / Grok Build v1.0.44 · high effort · grok-1-0-44-basic-r02-61e7dce0-20260929. Reward: 0.030785.. Agent time: 30m 3s. Recorded steps: 35grok-1-0-44-basic-r02-61e7dce0-20260929: 0.030785. Agent time: 30m 3s. Recorded steps: 35 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r04-recovery-20260923T212844Z. Reward: 0.000000 (assigned). Validation failed: missing submission.parquet or submission.csv. Agent time: 30m 3s. Recorded steps: 75base-sol-high-cli-0-153-4-r04-recovery-20260923T212844Z: 0.000000 (assigned zero: no valid artifact or verifier reward). Agent time: 30m 3s. Recorded steps: 75 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r03-recovery-20260923T212844Z. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 74base-sol-high-cli-0-153-4-r03-recovery-20260923T212844Z: 0.009092. Agent time: 30m 3s. Recorded steps: 74 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r01-recovery-20260923T212844Z. Reward: 0.024660.. Agent time: 28m 5s. Recorded steps: 80base-sol-high-cli-0-153-4-r01-recovery-20260923T212844Z: 0.024660. Agent time: 28m 5s. Recorded steps: 80 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r02-recovery-20260923T212844Z. Reward: 0.025398.. Agent time: 30m 3s. Recorded steps: 69base-sol-high-cli-0-153-4-r02-recovery-20260923T212844Z: 0.025398. Agent time: 30m 3s. Recorded steps: 69 gpt-5.6-sol / Codex v0.153.4 · high effort · base-sol-high-cli-0-153-4-r05-recovery-20260923T212844Z. Reward: 0.028513.. Agent time: 30m 3s. Recorded steps: 70base-sol-high-cli-0-153-4-r05-recovery-20260923T212844Z: 0.028513. Agent time: 30m 3s. Recorded steps: 70 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r01-20260923T050949Z. Reward: 0.042554.. Agent time: 29m 25s. Recorded steps: 80base-astra-high-cli-0-153-4-r01-20260923T050949Z: 0.042554. Agent time: 29m 25s. Recorded steps: 80 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r02-20260923T050949Z. Reward: 0.046185.. Agent time: 28m 22s. Recorded steps: 100base-astra-high-cli-0-153-4-r02-20260923T050949Z: 0.046185. Agent time: 28m 22s. Recorded steps: 100 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r05-20260923T050949Z. Reward: 0.048050.. Agent time: 29m 17s. Recorded steps: 91base-astra-high-cli-0-153-4-r05-20260923T050949Z: 0.048050. Agent time: 29m 17s. Recorded steps: 91 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r04-20260923T050949Z. Reward: 0.049333.. Agent time: 29m 23s. Recorded steps: 97base-astra-high-cli-0-153-4-r04-20260923T050949Z: 0.049333. Agent time: 29m 23s. Recorded steps: 97 gpt-6-astra / Codex v0.153.4 · high effort · base-astra-high-cli-0-153-4-r03-20260923T050949Z. Reward: 0.049784.. Agent time: 26m 56s. Recorded steps: 92base-astra-high-cli-0-153-4-r03-20260923T050949Z: 0.049784. Agent time: 26m 56s. Recorded steps: 92 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r04-20260924T221413Z. Reward: 0.019697.. Agent time: 11m 43s. Recorded steps: 39sol-medium-0-153-4-basic-r04-20260924T221413Z: 0.019697. Agent time: 11m 43s. Recorded steps: 39 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r03-20260924T221413Z. Reward: 0.026425.. Agent time: 24m 33s. Recorded steps: 47sol-medium-0-153-4-basic-r03-20260924T221413Z: 0.026425. Agent time: 24m 33s. Recorded steps: 47 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r01-20260924T221413Z. Reward: 0.027901.. Agent time: 13m 59s. Recorded steps: 41sol-medium-0-153-4-basic-r01-20260924T221413Z: 0.027901. Agent time: 13m 59s. Recorded steps: 41 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r05-20260924T221413Z. Reward: 0.034125.. Agent time: 11m 52s. Recorded steps: 39sol-medium-0-153-4-basic-r05-20260924T221413Z: 0.034125. Agent time: 11m 52s. Recorded steps: 39 gpt-5.6-sol / Codex v0.153.4 · medium effort · sol-medium-0-153-4-basic-r02-20260924T221413Z. Reward: 0.035517.. Agent time: 16m 34s. Recorded steps: 40sol-medium-0-153-4-basic-r02-20260924T221413Z: 0.035517. Agent time: 16m 34s. Recorded steps: 40 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r01-20260924T221413Z-retry01. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 117sol-max-0-153-4-basic-r01-20260924T221413Z-retry01: 0.009092. Agent time: 30m 3s. Recorded steps: 117 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r05-20260924T221413Z. Reward: 0.009092.. Agent time: 30m 2s. Recorded steps: 74sol-max-0-153-4-basic-r05-20260924T221413Z: 0.009092. Agent time: 30m 2s. Recorded steps: 74 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r02-20260924T221413Z. Reward: 0.035815.. Agent time: 30m 3s. Recorded steps: 82sol-max-0-153-4-basic-r02-20260924T221413Z: 0.035815. Agent time: 30m 3s. Recorded steps: 82 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r03-20260924T221413Z. Reward: 0.037559.. Agent time: 24m 39s. Recorded steps: 100sol-max-0-153-4-basic-r03-20260924T221413Z: 0.037559. Agent time: 24m 39s. Recorded steps: 100 gpt-5.6-sol / Codex v0.153.4 · max effort · sol-max-0-153-4-basic-r04-20260924T221413Z. Reward: 0.039252.. Agent time: 28m 9s. Recorded steps: 156sol-max-0-153-4-basic-r04-20260924T221413Z: 0.039252. Agent time: 28m 9s. Recorded steps: 156 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r05-3d6fca60. Reward: 0.009070.. Agent time: 30m 3s. Recorded steps: 63gemini-3-8-flash-high-basic-fixed-r05-3d6fca60: 0.009070. Agent time: 30m 3s. Recorded steps: 63 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r01-d0433654. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 56gemini-3-8-flash-high-basic-fixed-r01-d0433654: 0.009092. Agent time: 30m 3s. Recorded steps: 56 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r02-d237f45e. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 41gemini-3-8-flash-high-basic-fixed-r02-d237f45e: 0.009092. Agent time: 30m 3s. Recorded steps: 41 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r03-d237f45e. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 51gemini-3-8-flash-high-basic-fixed-r03-d237f45e: 0.009092. Agent time: 30m 3s. Recorded steps: 51 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-fixed-r04-d237f45e. Reward: 0.009092.. Agent time: 30m 5s. Recorded steps: 54gemini-3-8-flash-high-basic-fixed-r04-d237f45e: 0.009092. Agent time: 30m 5s. Recorded steps: 54 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r01-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 69gemini-3-8-flash-high-basic-r01-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 69 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r02-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 50gemini-3-8-flash-high-basic-r02-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 50 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r04-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 58gemini-3-8-flash-high-basic-r04-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 58 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r05-b9049e57. Reward: 0.009092.. Agent time: 30m 3s. Recorded steps: 56gemini-3-8-flash-high-basic-r05-b9049e57: 0.009092. Agent time: 30m 3s. Recorded steps: 56 gemini-3.8-flash / Gemini CLI v0.61.0 · high effort · gemini-3-8-flash-high-basic-r03-b9049e57. Reward: 0.009112.. Agent time: 30m 3s. Recorded steps: 60gemini-3-8-flash-high-basic-r03-b9049e57: 0.009112. Agent time: 30m 3s. Recorded steps: 60 0.00 0.01 0.02 0.03 0.04 0.05 Hidden NDCG@10 · Higher is better

One dot per qualified run, grouped by model, harness, and reasoning effort across the full history. Select a dot or its Open trace link to read the recording. Higher hidden quality NDCG@10 is better. Attempts without a valid artifact or verifier reward (including failed validation metrics) are shown at zero reward. All attempts remain in the table below; missing measured rewards and costs are shown as —, not zero. Calibration evidence only.

All attempts

Run Model Harness Effort Private reward Attempt cost
opus-high-01Full trace opus-5.0 Claude Code v2.1.251 high 0.021172 $1.30
opus-high-02Full trace opus-5.0 Claude Code v2.1.251 high 0.020738 $1.65
opus-high-03Full trace opus-5.0 Claude Code v2.1.251 high 0.030378 $1.88
opus-high-04Full trace opus-5.0 Claude Code v2.1.251 high 0.026023 $1.19
opus-high-05Full trace opus-5.0 Claude Code v2.1.251 high 0.009092 $2.69
opus-5-5-high-01Full trace opus-5.5 Claude Code v2.1.283 high 0.033498 $0.43
opus-5-5-high-02Full trace opus-5.5 Claude Code v2.1.283 high 0.038827 $0.42
opus-5-5-high-03Full trace opus-5.5 Claude Code v2.1.283 high 0.032849 $0.51
opus-5-5-high-04Full trace opus-5.5 Claude Code v2.1.283 high 0.022903 $0.54
opus-5-5-high-05Full trace opus-5.5 Claude Code v2.1.283 high 0.032805 $0.57
fable-5-1-high-01Full trace fable-5.1 Claude Code v2.1.288 high 0.034059 $1.41
fable-5-1-high-02Full trace fable-5.1 Claude Code v2.1.288 high 0.031604 $1.67
fable-5-1-high-03Full trace fable-5.1 Claude Code v2.1.288 high 0.030161 $1.75
fable-5-1-high-04Full trace fable-5.1 Claude Code v2.1.288 high 0.033316 $1.18
fable-5-1-high-05Full trace fable-5.1 Claude Code v2.1.288 high 0.021079 $1.40
sol-high-01Full trace gpt-5.6-sol Codex v0.147.0 high — $3.03
sol-high-02Full trace gpt-5.6-sol Codex v0.147.0 high 0.026471 $2.66
sol-high-03Full trace gpt-5.6-sol Codex v0.147.0 high 0.032421 $2.31
sol-high-04Full trace gpt-5.6-sol Codex v0.147.0 high 0.033728 $2.66
sol-high-05Full trace gpt-5.6-sol Codex v0.147.0 high 0.030634 $4.00
grok-high-01Full trace grok-4.6 Grok Build v1.0.44 high 0.008780 —
grok-high-02Full trace grok-4.6 Grok Build v1.0.44 high 0.030785 —
grok-high-03Full trace grok-4.6 Grok Build v1.0.44 high 0.009092 —
grok-high-04Full trace grok-4.6 Grok Build v1.0.44 high 0.008780 —
grok-high-05Full trace grok-4.6 Grok Build v1.0.44 high 0.008780 —
sol-0.153.4-high-01Full trace gpt-5.6-sol Codex v0.153.4 high 0.024660 $2.08
sol-0.153.4-high-02Full trace gpt-5.6-sol Codex v0.153.4 high 0.025398 $1.49
sol-0.153.4-high-03Full trace gpt-5.6-sol Codex v0.153.4 high 0.009092 $1.92
sol-0.153.4-high-04Full trace gpt-5.6-sol Codex v0.153.4 high — $1.95
sol-0.153.4-high-05Full trace gpt-5.6-sol Codex v0.153.4 high 0.028513 $1.81
astra-0.153.4-high-01Full trace gpt-6-astra Codex v0.153.4 high 0.042554 $6.67
astra-0.153.4-high-02Full trace gpt-6-astra Codex v0.153.4 high 0.046185 $8.49
astra-0.153.4-high-03Full trace gpt-6-astra Codex v0.153.4 high 0.049784 $8.05
astra-0.153.4-high-04Full trace gpt-6-astra Codex v0.153.4 high 0.049333 $7.01
astra-0.153.4-high-05Full trace gpt-6-astra Codex v0.153.4 high 0.048050 $8.06
sol-0.153.4-medium-01Full trace gpt-5.6-sol Codex v0.153.4 medium 0.027901 $0.98
sol-0.153.4-medium-02Full trace gpt-5.6-sol Codex v0.153.4 medium 0.035517 $0.94
sol-0.153.4-medium-03Full trace gpt-5.6-sol Codex v0.153.4 medium 0.026425 $1.26
sol-0.153.4-medium-04Full trace gpt-5.6-sol Codex v0.153.4 medium 0.019697 $1.03
sol-0.153.4-medium-05Full trace gpt-5.6-sol Codex v0.153.4 medium 0.034125 $0.90
sol-0.153.4-max-01Full trace gpt-5.6-sol Codex v0.153.4 max 0.009092 $3.50
sol-0.153.4-max-02Full trace gpt-5.6-sol Codex v0.153.4 max 0.035815 $2.08
sol-0.153.4-max-03Full trace gpt-5.6-sol Codex v0.153.4 max 0.037559 $2.55
sol-0.153.4-max-04Full trace gpt-5.6-sol Codex v0.153.4 max 0.039252 $4.16
sol-0.153.4-max-05Full trace gpt-5.6-sol Codex v0.153.4 max 0.009092 $2.02
gemini-3-8-flash-high-01Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.57
gemini-3-8-flash-high-02Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.49
gemini-3-8-flash-high-03Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.53
gemini-3-8-flash-high-04Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.60
gemini-3-8-flash-high-05Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009070 $0.85
gemini-3-8-flash-high-06Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.89
gemini-3-8-flash-high-07Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.65
gemini-3-8-flash-high-08Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009112 $0.73
gemini-3-8-flash-high-09Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.74
gemini-3-8-flash-high-10Full trace gemini-3.8-flash Gemini CLI v0.61.0 high 0.009092 $0.72