Gemini 2.5 Pro vs Kimi K2 Thinking
Kimi K2 Thinking edges ahead on overall intelligence (RunFree 45.2 vs 22.3). Here's how they stack up on benchmarks, price and specs.
Gemini 2.5 Pro
Google
Kimi K2 Thinking
MoonshotAI
Shared benchmarks (5)
Loading chart…
| Gemini 2.5 Pro | Kimi K2 Thinking | |
|---|---|---|
| RunFree Score | 22.3 | 45.2 |
| Blended price / 1M | $3.44 | $1.07 |
| Input / 1M | $1.25 | $0.60 |
| Output / 1M | $10.00 | $2.50 |
| Context window | 1.0M | 262K |
| Max output | 66K | 262K |
| Reasoning model | Yes | Yes |
| AIME 2025 | 88% | 94.5% |
| GPQA Diamond | 86.4% | 84.5% |
| Humanity's Last Exam | 21.6% | 23.9% |
| LiveCodeBench | 69% | 83.1% |
| SWE-Bench Verified | 59.6% | 71.3% |
| Wins | 2 | 9 |
A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.
Compare more: Gemini 2.5 Pro card · Kimi K2 Thinking card · full leaderboard