Kimi K2 Thinking
moonshotai· kimihealthyKimi K2 Thinking: curated reference profile, Commercial license
Kimi K2 Thinking: curated reference profile drawn from the model's published reports. Not a Supermagin measurement. Run the official eval in the Studio to earn a verified score.
Curated reference profile · not a Supermagin measurement
Model card & documentation
Kimi K2 Thinking
Curated reference profile · Commercial license · vK2 · 1.9s latency
These figures are drawn from the model's published reports and are NOT a Supermagin measurement. Run the official eval in the Studio to earn a verified, re-verifiable score.
Capabilities
- reasoning: 89%
- coding: 88%
- agent: 88%
- cybersecurity: 86%
Notes
- Low hallucination rate on audited evals.
- Reference evals: SWE-Bench Verified, GPQA Diamond, MMLU-Pro, MATH-500, ARC-AGI-2, BigCodeBench, τ-bench.
Pooled score
0%
credibility 100% · consistency 0.96
Score trend across attested runs
22941 total samples
More attested runs are needed to show a trend.
Category scores
Progress by year
Success rate
0%
Failure rate
0%
Hallucination
0%
Avg latency
1900ms
per task
Avg cost
$0.0040
per task
Calibration gap
+0.11
positive = overconfident
Top failure signals
Pooled brain diagnostics
Failure rate by task type
Curated reference profile, descriptive data, not a Supermagin measurement.