Kaelum Bench v0.2 · Public Calibration

Mistral Large 2512

Accounting Capstone · Run evidence

Provisional · Hybrid

Run identity

Model and configuration

Model display name
Mistral Large 2512
Exact model ID
mistralai/mistral-large-2512
Provider
Mistral AI
Exact provider route
openrouter/mistral
Runtime ID
openrouter-tool-free-non-streaming-v8
Runtime version
v8
Reasoning profile
native-default
Reasoning configuration
native-default
Tool access
None
Suite
Accounting Capstone
Validity
Provisional
Material configuration parameters
allow_fallbacks
false
data_collection
deny
max_attempts_per_task
1
max_concurrency
1
max_generation_metadata_lookups
1
max_output_tokens
34000
max_raw_response_bytes
16777216
max_request_bytes
1048576
metadata_timeout_seconds
60
request_timeout_seconds
300
require_parameters
true
temperature
0
zdr
false

Published score

Scoring evidence

Score
264.6 / 1000
Percentage
26.5%
Scoring method
Hybrid
Comparison protocol
Configuration-specific
Tested-model cost
$0.092
Judge cost
$3.32
Total cost
$3.41

Usage

Tokens and execution

Input tokens (tested model)
86,973
Output tokens (tested model)
32,960
Total tokens (tested model)
119,933
Attempted tasks
100 / 100
Valid responses
97 / 100
Invalid JSON
3
Schema failures
0
Provider failures
0
Missing responses
0

Judge evidence

Independent assessment

Judge model
openai/gpt-5.6-sol
Judge provider
OpenRouter (Azure EU)
Judge route
Not publicly released
Judge region
Not publicly released
Judge input tokens
243,034
Judge output tokens
59,877
Judge tokens
302,911
Judge assessments
97
Assessment not required
0
Judge retries
0

Release provenance

Versioned run evidence

Benchmark ID
FMB-CAP-ACC-03
Benchmark version
0.3.0-dev
Scorer ID
fmb-live-scorer-v1
Configuration key
config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4
Campaign ID
dbe47734-1b0c-5687-87ca-9e81f03a462a
Comparison group ID
accounting-capstone-0.3.0-dev-configuration-specific-v1
Started at
Completed at
Run ID
fca1649b-9e04-5d7d-81c3-2a12a65daa0b
Signed release ID
9d07d6d8-80f4-4bca-9adf-1f436336d09d
Release ID
80817257-aa7f-4fb9-867b-66e9ed813de9
Manifest SHA-256
d82a32b09acf027f94de5fe162ca71dabb3a389a4e2b12f58fa3d1faec73a3c8
Source aggregate
fmb-live-runs-capstone.json
Source aggregate SHA-256
922b6a973199cf2ce4c494392dce2e6636b459127a51b6ad4a065190241fb9bb
Source aggregate bytes
17,397

Authenticated publication

Signed release evidence

The sanitized single-run JSON is a derived projection and is not separately signed. The Ed25519 signature authenticates the exact public manifest bytes, including the release inventory. The manifest in turn binds this run's source aggregate by its SHA-256 digest and byte size.

Verify this evidence
  1. Verify the detached Ed25519 signature over the domain-prefixed exact manifest bytes using the published public key.
  2. Confirm that the sidecar payload SHA-256 equals the manifest SHA-256 shown above.
  3. Hash the source aggregate and compare its SHA-256 and byte size with the signed manifest entry.
  4. Resolve this run ID through the public run index and match its campaign ID inside that aggregate.
node -e 'const fs=require("node:fs"),c=require("node:crypto"),m=fs.readFileSync("public-manifest.json"),s=JSON.parse(fs.readFileSync("public-manifest-signature.json","utf8")),k=fs.readFileSync("kaelum-bench-public-release-20260718-v1.pem");console.log(c.verify(null,Buffer.concat([Buffer.from("kaelum-bench-fmb-public-release-v1\0"),m]),k,Buffer.from(s.signature_base64,"base64")))'