moonshotai/kimi-k3-free

openai attested

Attestation smg:attest:v1:d1e204d574cbcedce4b4fe324a3fef2ba927b595bc987625012ed2de9e02bb7c

Overall score

33%

generation

100%

1 task

medium

50%

2 tasks

text

33%

3 tasks

1 task

easy

1 task

The real tests (3)

Every task this model was actually run on. Re-runnable and verifiable.

#	Task	Status	Score
1	Math: solve a linear equation	error	0%
2	Classification — sentiment	error	0%
3	Kimi smoke test	success	100%

Prompts + scoring are snapshotted with the proof. Re-runnable without the original workspace.

#	Task	Judge	Prompt	Expected
1	Math: solve a linear equation	exact	Solve for x: 3x + 7 = 22. Give ONLY the numeric value of x.	5
2	Classification — sentiment	exact	Classify the sentiment of this review as positive, negative, or neutral: "Absolutely loved it — fast, accurate, and easy to use." Answer with one word.	positive
3	Kimi smoke test	normalized	Reply with exactly the single word: banana	banana

Task-set commitment: smg:task-set:v1:56029888419428a504c89279f13f9b5ce9bd5e60a64f5b10d154923c6ec08d84

Re-run these exact tasks with your own model + key and compare against the published scores. The task set is pinned by hash, so it can't be swapped.

Reproduce with your own key (BYOK, never stored)

Provider

Model ID

API key

3 tasks · task-set pinned

This list is the attestation payload published with the run. To verify it, re-run the same tasks with the same scoring and compare the hash above.