Model monitor
Qwen 3 30B A3B Instruct Reference
qwen/qwen3-30b-a3b-instruct-2507 · via openrouter
As of 2026-08-05: reference route · 22 complete panels attest measurement across 4 task families.
Served route, trailing 30 days: median latency 2.4 s · p95 5.4 s across 185 probe calls · served by StreamLake (185), unrecorded (5). Observed at panel time — a few calls a day, not continuous uptime.
Reference route: this model is the co-probed confound control. It never opens a public incident — its record attests measurement, not verdicts.
Certified claim, per family: H0: E[panel_mean_t | prior completed panels] ≥ frozen_null_floor. Fixed panel composition does not assume or establish temporal independence. Recent panels below link to their hash-committed evidence.
Task family
Structured output
- Frozen null floor
- 0.700
- Anytime level α
- 0.050
- Completed panels
- 2
- CS lower
- 0.000
- CS upper
- 1.000
Panel record — 2 completed panels
| Cycle | Completed | Member scores | Mean | Evidence |
|---|---|---|---|---|
| 44 | 2026-08-05 14:00 UTC | 1.001.001.001.001.00 | 1.000 | afb1427e8134… |
| 43 | 2026-08-05 12:58 UTC | 1.001.001.001.001.00 | 1.000 | 129ef9fe6da1… |
Newest first. A failed member scores 0 and stays on the record. Each evidence link opens the panel’s full hash-committed record.
Epoch & design record
- Current epoch
cae9b52b-1f14-4aa4-a50f-c33a6b4fa544- Opened
- 2026-08-05 12:27 UTC
- Previous epoch
55048047-8796-48c4-bded-7f7538ceb6c9- Transition
- checker_refresh
- Design hash
8a4f5431d708d308ccd859fc31d097a5db0297535ace2795cab39b5f087eb318- Panel hash
a37ad21aa4b8c3e16dbae958c68a70064a9d95487e131d832f2c601f7fdacf14- Pool hash
8e9496011afbb949e38b3facc664e6dd560f1c5d2155fd424fcb720d084c69ee- Panel size
- 5
- Terminal failure
- zero — a failed member scores 0 and stays on the record
- Pool version
structured-output-v3- Checker version
structured_output-v2- Reference mean μ₀
- 0.700
- Minimum effect δ
- 0.000
- Evidence log e
- -0.23 · max 0.00 · alarm at 3.00 (= ln 1/α)
- Raw scores kept
- 10
- Provider spend, this epoch
- $0.0003211
The persisted monitor state is the authority a certificate replays byte-for-byte; the chart band above is a faithful replay of the same recorded panel means. Spend sums completed probe runs and includes reserved estimates where a run’s true cost was unrecoverable.
Task family
Extraction
- Frozen null floor
- 0.700
- Anytime level α
- 0.050
- Completed panels
- 2
- CS lower
- 0.000
- CS upper
- 1.000
Panel record — 2 completed panels
| Cycle | Completed | Member scores | Mean | Evidence |
|---|---|---|---|---|
| 44 | 2026-08-05 13:59 UTC | 1.001.001.000.000.67 | 0.733 | 1c479e022a50… |
| 43 | 2026-08-05 12:36 UTC | 1.001.001.000.000.67 | 0.733 | 38d41eb54cbc… |
Newest first. A failed member scores 0 and stays on the record. Each evidence link opens the panel’s full hash-committed record.
Epoch & design record
- Current epoch
bf4e491f-636b-4982-b8e7-3ac9715fe38c- Opened
- 2026-08-05 12:27 UTC
- Previous epoch
21f69ed5-a596-4127-86cb-3d8dab24de2a- Transition
- checker_refresh
- Design hash
a2749265eac9731c94d1b8cada6fedc0e453bbc919053c455268b3a7eb248a61- Panel hash
1703e9221c9ce6ce1a9f69974cf0fd77056ac1ee4009dec47e3e6f23be2d4351- Pool hash
51802fc8964f7d9927bcabfae23b4bd2f0905e8977c9f8fb4ce50884ab0fbba6- Panel size
- 5
- Terminal failure
- zero — a failed member scores 0 and stays on the record
- Pool version
extraction-v3- Checker version
extraction-v2- Reference mean μ₀
- 0.700
- Minimum effect δ
- 0.000
- Evidence log e
- -0.04 · max 0.00 · alarm at 3.00 (= ln 1/α)
- Raw scores kept
- 10
- Provider spend, this epoch
- $0.0000912
The persisted monitor state is the authority a certificate replays byte-for-byte; the chart band above is a faithful replay of the same recorded panel means. Spend sums completed probe runs and includes reserved estimates where a run’s true cost was unrecoverable.
Task family
Instruction following
- Frozen null floor
- 0.700
- Anytime level α
- 0.050
- Completed panels
- 9
- CS lower
- 0.102
- CS upper
- 1.000
Panel record — 9 completed panels
| Cycle | Completed | Member scores | Mean | Evidence |
|---|---|---|---|---|
| 44 | 2026-08-05 13:39 UTC | 1.001.000.830.861.00 | 0.938 | d67f8ca27239… |
| 43 | 2026-08-05 12:36 UTC | 1.001.000.830.861.00 | 0.938 | 35b657fa3b89… |
| 42 | 2026-08-05 11:35 UTC | 1.001.000.830.861.00 | 0.938 | 2ba3abfe366b… |
| 41 | 2026-08-05 10:31 UTC | 1.001.000.830.861.00 | 0.938 | c3239484c8b7… |
| 40 | 2026-08-05 09:31 UTC | 1.001.000.830.861.00 | 0.938 | 147cbb80a71e… |
| 39 | 2026-08-05 08:26 UTC | 1.001.000.830.861.00 | 0.938 | 1ee4482d76b0… |
| 38 | 2026-08-05 07:21 UTC | 1.001.000.830.861.00 | 0.938 | 112c0b9911f0… |
| 37 | 2026-08-05 06:21 UTC | 0.831.000.830.861.00 | 0.905 | 0cab8444ef38… |
| 36 | 2026-08-05 05:21 UTC | 1.001.000.830.861.00 | 0.938 | e99af196b705… |
Newest first. A failed member scores 0 and stays on the record. Each evidence link opens the panel’s full hash-committed record.
Epoch & design record
- Current epoch
2c5cd834-3470-4b44-bda8-0608c4762148- Opened
- 2026-08-05 04:17 UTC
- Design hash
4f5cc6b9ff4ce026ccab93f5a3c8241f78eb005bc8b8068e4c701e9236504412- Panel hash
e7dfea1f343f7bf37e066a1117ca21f3438e804ad61437bf72d810640cef7e71- Pool hash
9c5d065322394a6fb18c6d7f90c5bb63f00781f3e4c4aaa663536f76bb8ba7f9- Panel size
- 5
- Terminal failure
- zero — a failed member scores 0 and stays on the record
- Pool version
instruction_following-v3- Checker version
instruction_following-v1- Reference mean μ₀
- 0.700
- Minimum effect δ
- 0.000
- Evidence log e
- -0.18 · max 0.00 · alarm at 3.00 (= ln 1/α)
- Raw scores kept
- 45
- Provider spend, this epoch
- $0.0002279
The persisted monitor state is the authority a certificate replays byte-for-byte; the chart band above is a faithful replay of the same recorded panel means. Spend sums completed probe runs and includes reserved estimates where a run’s true cost was unrecoverable.
Task family
Math
- Frozen null floor
- 0.700
- Anytime level α
- 0.050
- Completed panels
- 9
- CS lower
- 0.164
- CS upper
- 1.000
Panel record — 9 completed panels
| Cycle | Completed | Member scores | Mean | Evidence |
|---|---|---|---|---|
| 44 | 2026-08-05 13:34 UTC | 1.001.001.001.001.00 | 1.000 | e44f478ef44e… |
| 43 | 2026-08-05 12:31 UTC | 1.001.001.001.001.00 | 1.000 | 6762e7eabd27… |
| 42 | 2026-08-05 11:32 UTC | 1.001.001.001.001.00 | 1.000 | 5c7d0eee2647… |
| 41 | 2026-08-05 10:26 UTC | 1.001.001.001.001.00 | 1.000 | 95634fbacd3a… |
| 40 | 2026-08-05 09:23 UTC | 1.001.001.001.001.00 | 1.000 | b39114bd1019… |
| 39 | 2026-08-05 08:17 UTC | 1.001.001.001.001.00 | 1.000 | ab8d0960169b… |
| 38 | 2026-08-05 07:16 UTC | 1.001.001.001.001.00 | 1.000 | ee6fab97afd4… |
| 37 | 2026-08-05 06:09 UTC | 1.001.001.001.001.00 | 1.000 | 1ff8ec2ebead… |
| 36 | 2026-08-05 05:08 UTC | 1.001.001.001.001.00 | 1.000 | fd33f54206ef… |
Newest first. A failed member scores 0 and stays on the record. Each evidence link opens the panel’s full hash-committed record.
Epoch & design record
- Current epoch
f632e870-72ee-4ce5-bb51-fd0001dac3a3- Opened
- 2026-08-05 04:17 UTC
- Design hash
fdf94065c55c2ee7d86701efc50be0f5abdc5f02a236f6df52c2ac6f7db801eb- Panel hash
882f3932d07aeb85c4f6406a550d8ad14512e70d3df2432fe7aab03d0508bc75- Pool hash
7ed49fa9a63ba0e0907ff8326de00a843a926618f6d0dec40aa8e491d041e99b- Panel size
- 5
- Terminal failure
- zero — a failed member scores 0 and stays on the record
- Pool version
math-v4- Checker version
math-v1- Reference mean μ₀
- 0.700
- Minimum effect δ
- 0.000
- Evidence log e
- -0.23 · max 0.00 · alarm at 3.00 (= ln 1/α)
- Raw scores kept
- 45
- Provider spend, this epoch
- $0.0020292
The persisted monitor state is the authority a certificate replays byte-for-byte; the chart band above is a faithful replay of the same recorded panel means. Spend sums completed probe runs and includes reserved estimates where a run’s true cost was unrecoverable.