Compare
Kimi K3 vs Mercury 2.5 Preview
Kimi K3 (Moonshot) and Mercury 2.5 Preview (Inception) compared on benchmarks, pricing, context window, and use-case rankings.
- Mercury 2.5 Preview is cheaper on input tokens — $0.04 vs $2.55 per 1M.
- Kimi K3 has a larger context window (1M vs 260K tokens).
| Attribute | Kimi K3 | Mercury 2.5 Preview |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 158 | — |
| Coding | 97 | — |
| Math | 81 | — |
| Reasoning & Knowledge | 73 | — |
| Agentic & Tools | 80 | — |
| Specifications | ||
| Developer | Moonshot | Inception |
| Family | Kimi | — |
| Released | Jul 16, 2026 | Aug 31, 2026 |
| Parameters | 2.8T | — |
| Availability | Open weights (non-commercial) | — |
| Context window | 1M | 260K |
| Price — $/M input | $2.55 | $0.04 |
| Price — $/M output | $12.75 | $0.15 |
| Inputs | text, image, video | text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 97% | — |
| APEX | 39% | — |
| ARC-AGI | 95% | — |
| ARC-AGI-2 | 60% | — |
| GPQA Diamond | 93% | — |
| Humanity's Last Exam | 47% | — |
| SciCode | 60% | — |
| SimpleBench | 61% | — |
| SimpleQA Verified | 51% | — |
| WebDev Arena | 1674 | — |
| WeirdML | 83% | — |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Which is cheaper, Kimi K3 or Mercury 2.5 Preview?
Mercury 2.5 Preview is cheaper on input tokens at $0.04 per million, versus $2.55 (representative OpenRouter pricing).
Which has a larger context window, Kimi K3 or Mercury 2.5 Preview?
Kimi K3 supports up to 1M tokens, compared with 260K for the other.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.