Skip to main content
Meo

MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is moonshotai's model. On the un-leaked meo benchmark it ranks #25 of 82 with 66.9% accuracy and an Effective Value (𝕍) of 0.0031 β€” earning a correct answer for about $0.0139 in 88s each.

as of 2026-10-18

meo rank
#25
of 82
Accuracy
66.9%
overall
𝕍 index (top=100)
0.073
raw 𝕍 0.0031 Β· N=10
$ / correct
$0.0139
88s each

Per-domain accuracy

168 correct of 250 questions asked across 11 domains Β· answer rate 100% Β· macro accuracy 74.9%. Headline accuracy is micro-averaged per meo’s methodology; per-domain question counts (correct/asked) are shown so you can judge significance.

State tracking
100%1/1
Theory of mind
100%3/3
CSP (unsatisfiable)
94%15/16
Regex automaton
94%15/16
Tape machine
93%14/15
Base-rate bias
78%32/41
Logic / math / CS
74%25/34
Framework bias
67%2/3
Perceptual illusions
52%53/102
Watson-Glaser
50%2/4
Long arithmetic
40%6/15

Efficiency

Cost per correct
$0.0139
Seconds per correct
88
Tokens per correct
3,392
Correct answers
168 / 250
Total benchmark cost
$2.34
Avg tokens / item
2,279

Model details

Released
2026-06-12
Weights
Open
Context
262K
Max output
236K
Knowledge cutoff
β€”
Price in
$0.67/M
Price out
$3.35/M
Modality
text+image->text
View on OpenRouter β†—Hugging Face β†—

Sources: openrouter Β· meo

FAQ

How accurate is MoonshotAI: Kimi K2.7 Code?

MoonshotAI: Kimi K2.7 Code scores 66.9% overall on the meo benchmark (rank #25 of 82), an un-leaked private holdout graded objective-first.

What is MoonshotAI: Kimi K2.7 Code's Effective Value?

Its Effective Value (𝕍) is 0.0031 at N=10, Ο‰=1, Ξ΄=1.5 β€” a fused metric of accuracy, speed, cost, and error-cascade. 𝕍 rankings shift with task depth.

How much does MoonshotAI: Kimi K2.7 Code cost per correct answer?

About $0.0139 per correct answer (3,392 tokens, 88 seconds each) at benchmark-time pricing via OpenRouter.

Is MoonshotAI: Kimi K2.7 Code open weights?

Yes β€” MoonshotAI: Kimi K2.7 Code is released with open weights.

Benchmark updates affecting this model

  • 2026-06-12Added moonshotai/kimi-k2.7-code

    Benchmarked MoonshotAI Kimi K2.7 Code (shipped 2026-06-12, vision + reasoning, 262K context) over the full holdout under the standard protocol. Concise (~1.6k output tokens/item); the full battery cost $2.34, 0 errors.

  • 2026-06-09majorlogic_math_cs ground truth was broken β€” culled and rebuilt with solver-verified items

    A 5-lab frontier jury revealed that 29 of 37 LLM-authored logic_math_cs items had broken ground truth: on most, five independent frontier models unanimously concluded the clue sets were contradictory while the stored answer claimed a number, and on eight, all five agreed on the SAME different number (author arithmetic errors). Models were being marked wrong for being right. The 29 were retired (full audit published in the repo) and the domain rebuilt with generator-as-oracle items: an embedded constraint solver PROVES each puzzle has exactly one solution (or provably none), verified by an independent exhaustive enumerator. A 3-round difficulty study found frontier models saturate consistent human-scale logic puzzles, so items use anonymous global constraints and carry a measured difficulty gradient.

  • 2026-06-08majorCorrected base_bias grading (LLM-equivalence judge fix)

    The LLM-equivalence grader uses a reasoning model whose verdict token budget was too small, so its YES/NO answer was emitted as empty and silently counted as a failure. This understated the base_bias domain to ~7% for every model when the true accuracy is ~85-90%. We raised the judge budget, excluded its reasoning tokens from the verdict, switched to verbosity-robust conclusion matching, and re-graded the whole board.

Full benchmark changelog β†’

Embed this ranking

Show MoonshotAI: Kimi K2.7 Code’s meo rank on your site β€” the badge links back here.

Related: all Moonshot AI models Β· Multi-step state tracking domain Β· best Effective Value Β· biggest movers Β· methodology Β· full leaderboard.