Rewrite · 4 checks · max 400 tokens · benched 2026-09-16

Kimi K3 vs Kimi K2.7 Code vs Kimi K2.6 vs Kimi K2.5 on product update to a 280-character post

Moonshotai models side by side on "Product update to a 280-character post": Kimi K2.7 Code scores 9/10; Kimi K2.7 Code is the cheapest answer scoring 8+ at $0.80 per 1,000 runs. Outputs, checks, judge reasons, latency and cost.

The prompt every model received

User

Turn this update into a single social media post of at most 280 characters. It must mention "v2.0" and end with the hashtag #OpenSource. Output only the post.

Update: Version 2.0 of our command-line tool is out. It is three times faster on large repositories, adds a built-in diff viewer, and is now licensed under MIT so anyone can contribute.

Rubric for the judge: Punchy post under 280 characters that mentions v2.0, the speed gain, the diff viewer and MIT, ending with #OpenSource.

Side by side

Every cell is one OpenRouter call at temperature 0 with the prompt's token cap and reasoning effort "low" where the model supports it. Cost is usage × the catalogue rate in models.json. Quality is one judge call to anthropic/claude-haiku-4.5 against the prompt's rubric, cached per prompt version.

Kimi K3

moonshotai/kimi-k3

9/10

Latency: 788ms
Cost: $0.00281
Per 1,000: $2.81

205 in · 202 out (160 reasoning) · 17 words · checks 4/4

max_chars
contains
regex
contains

CLI tool v2.0 is out: 3x faster on large repos, built-in diff viewer, MIT licensed—contributions welcome! #OpenSource

Judge: Post is 109 characters (well under 280), mentions v2.0, speed gain, diff viewer, MIT licensing, and ends with #OpenSource; only minor issue is it doesn't explicitly state 'anyone can contribute' though 'contributions welcome' conveys the intent.

Kimi K2.7 Code

moonshotai/kimi-k2.7-code

9/10

top judge scorecheapest scoring 8+

Latency: 1.0s
Cost: $0.00080
Per 1,000: $0.80

88 in · 212 out (171 reasoning) · 25 words · checks 4/4

max_chars
contains
regex
contains

🚀 v2.0 of our CLI tool is here — 3x faster on large repos, built-in diff viewer, and now MIT-licensed so anyone can contribute. #OpenSource

Judge: Post is 119 characters (well under 280), mentions v2.0, speed gain, diff viewer, and MIT licensing, ends with #OpenSource hashtag, and is punchy and engaging; only minor issue is it could have been slightly more explicit about 'anyone can contribute' but the meaning is clear.

Kimi K2.6

moonshotai/kimi-k2.6

1/10

failed: empty output (finish_reason length)

Latency: 1.1s
Cost: $0.00649
Per 1,000: $6.49

89 in · 1600 out (1600 reasoning) · 0 words · checks 1/4

max_chars
contains
regex
contains

(empty output)

Judge: The output is completely empty, failing to provide any social media post whatsoever.

Kimi K2.5

moonshotai/kimi-k2.5

9/10

Latency: 837ms
Cost: $0.00347
Per 1,000: $3.47

89 in · 1526 out (1486 reasoning) · 26 words · checks 4/4

max_chars
contains
regex
contains

v2.0 of our command-line tool is here! It's 3x faster on large repos, adds a built-in diff viewer, and is now MIT licensed. Contributions welcome! #OpenSource

Judge: Post is 168 characters, mentions v2.0, speed gain (3x faster), diff viewer, MIT licensing, and ends with #OpenSource hashtag as required; only minor issue is not explicitly stating 'anyone can contribute' though 'Contributions welcome' conveys this.

Frequently asked

What does this prompt test?

Rewrite: Punchy post under 280 characters that mentions v2.0, the speed gain, the diff viewer and MIT, ending with #OpenSource. The deterministic checks are max_chars, contains, regex, contains.

Which model should I pick for this task?

If the judge's bar of 8/10 is good enough for you, Kimi K2.7 Code at $0.80 per 1,000 runs. If you need the top score, Kimi K2.7 Code at $0.80 per 1,000 runs.

Same prompt, other families

Run it yourself

Re-run this prompt on Moonshotai with your own OpenRouter key, or tweak the wording and see what changes.

Side by side

Kimi K3

Kimi K2.7 Code

Kimi K2.6

Kimi K2.5

Frequently asked

Same prompt, other families

Stop overpaying for AI tools