Claude Opus 4.8 vs Kimi K2 Thinking
Claude Opus 4.8 edges ahead on overall intelligence (RunFree 94.7 vs 45.2). Here's how they stack up on benchmarks, price and specs.
Claude Opus 4.8
Anthropic
Kimi K2 Thinking
MoonshotAI
Shared benchmarks (4)
Loading chart…
| Claude Opus 4.8 | Kimi K2 Thinking | |
|---|---|---|
| RunFree Score | 94.7 | 45.2 |
| Blended price / 1M | $10.00 | $1.07 |
| Input / 1M | $5.00 | $0.60 |
| Output / 1M | $25.00 | $2.50 |
| Context window | 1M | 262K |
| Max output | 128K | 262K |
| Reasoning model | Yes | Yes |
| GPQA Diamond | 93.6% | 84.5% |
| Humanity's Last Exam | 49.8% | 23.9% |
| SWE-Bench Verified | 88.6% | 71.3% |
| Terminal-Bench | 74.6% | 47.1% |
| Wins | 6 | 4 |
A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.
Compare more: Claude Opus 4.8 card · Kimi K2 Thinking card · full leaderboard