Kimi K3 vs Trinity Large Thinking
Kimi K3 (Moonshot) and Trinity Large Thinking (Arcee AI) compared on benchmarks, pricing, context window, and use-case rankings.
- Trinity Large Thinking is cheaper on input tokens — $0.25 vs $2.55 per 1M.
- Kimi K3 has a larger context window (1M vs 262K tokens).
- Kimi K3 ranks higher for coding (97th vs 18th percentile).
| Attribute | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 158 | — |
| Coding | 97 | 18 |
| Math | 81 | — |
| Reasoning & Knowledge | 73 | 19 |
| Agentic & Tools | 80 | 58 |
| Specifications | ||
| Developer | Moonshot | Arcee AI |
| Family | Kimi | — |
| Released | Jul 16, 2026 | Apr 1, 2026 |
| Parameters | 2.8T | — |
| Availability | Open weights (non-commercial) | — |
| Context window | 1M | 262K |
| Price — $/M input | $2.55 | $0.25 |
| Price — $/M output | $12.75 | $0.80 |
| 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% | 75% |
| Humanity's Last Exam | 47% | 16% |
| SciCode | 60% | 41% |
| SimpleBench | 61% | — |
| SimpleQA Verified | 51% | — |
| WebDev Arena | 1674 | 1238 |
| WeirdML | 83% | — |
| τ²-bench | — | 90% |
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 Trinity Large Thinking?
Trinity Large Thinking is cheaper on input tokens at $0.25 per million, versus $2.55 (representative OpenRouter pricing).
Which has a larger context window, Kimi K3 or Trinity Large Thinking?
Kimi K3 supports up to 1M tokens, compared with 262K for the other.
Which is better for coding, Kimi K3 or Trinity Large Thinking?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 18th percentile among the models tracked on Model Beat.
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.