LLM Leaderboard
Kimi K2 Thinking
by MoonshotAI Reasoning
RunFree Score
45.2
#11 overall
Blended price
$1.07
per 1M tokens
Context
262K
tokens
Max output
262K
tokens
Output speed
—
tokens / sec
Latency (TTFT)
—
first token
Uptime
100.0%
last 24h
Providers
3
serving this model
Capability profile
Loading chart…
Compare Kimi K2 Thinking
See it side by side with any other model — benchmarks, price and specs.
Benchmark results
| Benchmark | Category | Score | As of | Source |
|---|---|---|---|---|
| Terminal-Bench | agentic | 47.1% | Nov 6, 2025 | cite |
| LiveCodeBench | coding | 83.1% | Nov 6, 2025 | cite |
| SWE-Bench Verified | coding | 71.3% | Nov 6, 2025 | cite |
| Humanity's Last Exam | knowledge | 23.9% | Nov 6, 2025 | cite |
| MMLU-Pro | knowledge | 84.6% | Nov 6, 2025 | cite |
| AIME 2025 | math | 94.5% | Nov 6, 2025 | cite |
| GPQA Diamond | reasoning | 84.5% | Nov 6, 2025 | cite |
Every score links to its original source. See our methodology for how the RunFree Score is computed.
API pricing
- Input
- $0.60 / 1M
- Output
- $2.50 / 1M
- Cached input
- $0.60 / 1M
- Blended (3:1)
- $1.07 / 1M
Specifications
- Provider
- MoonshotAI
- Context window
- 262K
- Max output
- 262K
- Reasoning model
- Yes
- Modality
- text
- Released
- Nov 6, 2025