GPT-5.6 Terra vs Kimi K3
GPT-5.6 Terra (OpenAI) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- GPT-5.6 Terra leads on overall intelligence (ECI 159 vs 158).
- Kimi K3 is cheaper on input tokens — $1.44 vs $2.00 per 1M.
- GPT-5.6 Terra has a larger context window (1.1M vs 1M tokens).
- Kimi K3 ranks higher for coding (94th vs 73th percentile).
| Attribute | GPT-5.6 Terra | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 159 | 158 |
| Coding | 73 | 94 |
| Math | 90 | 73 |
| Reasoning & Knowledge | 67 | 69 |
| Agentic & Tools | 61 | 66 |
| Specifications | ||
| Developer | OpenAI | Moonshot |
| Family | GPT | Kimi |
| Released | Jul 9, 2026 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | API access | Open weights (non-commercial) |
| Context window | 1.1M | 1M |
| Price — $/M input | $2.00 | $1.44 |
| Price — $/M output | $12.00 | $9.00 |
| Inputs | file, image, text | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 100% | 97% |
| APEX | 58% | 51% |
| ARC-AGI | 97% | 95% |
| ARC-AGI-2 | 84% | 60% |
| GPQA Diamond | 93% | 93% |
| Humanity's Last Exam | 43% | 47% |
| SciCode | 55% | 60% |
| SimpleBench | 49% | 61% |
| SimpleQA Verified | 43% | 51% |
| WebDev Arena | 1521 | 1674 |
| WeirdML | 78% | 83% |
| τ²-bench | 86% | — |
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
Is GPT-5.6 Terra better than Kimi K3?
On Epoch AI's Capabilities Index, GPT-5.6 Terra scores higher (159) than Kimi K3 (158). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, GPT-5.6 Terra or Kimi K3?
Kimi K3 is cheaper on input tokens at $1.44 per million, versus $2.00 (representative OpenRouter pricing).
Which has a larger context window, GPT-5.6 Terra or Kimi K3?
GPT-5.6 Terra supports up to 1.1M tokens, compared with 1M for the other.
Which is better for coding, GPT-5.6 Terra or Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 94th vs 73th 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.