Actuary
← Z.ai GLM 5.2

Evidence block

Instruction following · cycle 33

z-ai/glm-5.2 · 2026-08-05 02:15:04 UTC

This page is the full public record of one completed panel — the record’s hash-committed unit of evidence. Its identity is its hash; nothing here can change without changing the URL.

Identity

What this block is.

Panel mean
1.000
Members
5
Checker scored
5
Frozen floor
0.700
Anytime level α
0.050
Hashes and versions
Evidence hash
833129bee17e43fb86c9fda12aa08e4e6242a44f2f7453691f33fb0325523707
Design hash
4f5cc6b9ff4ce026ccab93f5a3c8241f78eb005bc8b8068e4c701e9236504412
Panel hash
e7dfea1f343f7bf37e066a1117ca21f3438e804ad61437bf72d810640cef7e71
Stream
1ca75a9f-6952-4c04-9b8a-1049aaa718a2
Epoch
37cb9150-9ea9-4f2f-baa9-815ec952f905
Pool version
instruction_following-v3
Checker version
instruction_following-v1
Panel size
5
Provider spend
$0.0071708

Checker layer

Panel members.

# Item Item id Outcome Score
1 instruction-following-015 26a44f13-e4a8-4273-9cfd-5adce0f3eec9 ok 1.00
2 instruction-following-045 462a27a2-2b9a-417e-b2c3-b20776fad9a0 ok 1.00
3 instruction-following-075 38ede11b-3d52-4905-a6a4-8ee6684146e4 ok 1.00
4 instruction-following-105 9294d9d8-5c71-4d76-b053-b5cefc08d0e1 ok 1.00
5 instruction-following-135 7d213d46-039d-4f3a-aecf-c785ef61cc80 ok 1.00

Deterministic checkers score every response in [0, 1]; a member that ends in a terminal failure scores 0 and stays on the record. Item text stays unpublished so nobody can tune against the panel — identity travels as the item id and its pool source id.

Capture layer

Provider requests.

# Provider Upstream Response model Response id Finish Latency ms Tokens in Tokens out Cost Output SHA-256 Observed
1 openrouter Novita z-ai/glm-5.2 gen-1785896049-OD0PHQcT3aeqcumUDcAM stop 18047 52 626 $0.00121 4b8fc6fd0643f0019cef3c4233d295f10db26ce957317f14837300b0f860b987 2026-08-05 02:14:27 UTC
2 openrouter Novita z-ai/glm-5.2 gen-1785896049-JpdB5n50OtScoYY0L5GU stop 9109 61 327 $0.0006524 fcc5ce047f7912486ef1a6fab4c7df803541e1770a5919c95683e21b48bb0d17 2026-08-05 02:14:18 UTC
3 openrouter Novita z-ai/glm-5.2 gen-1785896049-4PM379vHt8mH4wgAAqbV stop 39335 55 1665 $0.0031685 039421f4cfea44e05c008b6e900c34e3dbaf2a7c52f5c5b45ba2fae6f8e5a0d8 2026-08-05 02:14:48 UTC
4 openrouter Novita z-ai/glm-5.2 gen-1785896049-T4t54hkeHPRWQVyenHLY stop 15663 50 617 $0.0011919 6804ca245085b8c5ff4f2e331353e19aa52902124c66d5fcc46728e13d5f6aa8 2026-08-05 02:14:25 UTC
5 openrouter Novita z-ai/glm-5.2 gen-1785896072-3rRelJKUiRKI0zVnS8Bq stop 32263 61 484 $0.000948 1ae4323e07007b052bb7f38ff4ab1ca0ef9e12498d537111ad88e9441ccde736 2026-08-05 02:15:04 UTC

Everything a probe captures, as captured. Raw model text is scrubbed thirty days after the run; its SHA-256, the outcome and the score are permanent. Costs are provider-reported and include reserved estimates where a run’s true cost was unrecoverable; a dash is a field the provider did not return.

Verify

Recompute the hash yourself.

The JSON twin of this page carries the exact evidence object this URL is named after. Canonicalise it per RFC 8785 and hash it; the digest must equal the address of this page.

GET /api/v1/evidence/833129bee17e…

curl -s https://actuary.sh/api/v1/evidence/833129bee17e43fb86c9fda12aa08e4e6242a44f2f7453691f33fb0325523707 \
  | jq -cjS .evidence | shasum -a 256

For this object’s field types, jq -cjS reproduces RFC 8785 canonical form, and the JSON twin serves the hashed bytes verbatim. Blocks of exactly this shape appear verbatim in signed certificates — verify one offline, or read how the e-process turns panel means into an alarm.