GPT-5.4 Pro vs Kimi K3
GPT-5.4 Pro (OpenAI) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- GPT-5.4 Pro leads on overall intelligence (ECI 159 vs 158).
- Kimi K3 is cheaper on input tokens — $2.10 vs $30.00 per 1M.
- GPT-5.4 Pro has a larger context window (1.1M vs 1M tokens).
| Attribute | GPT-5.4 Pro | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 159 | 158 |
| Coding | — | 97 |
| Math | 96 | 82 |
| Reasoning & Knowledge | 76 | 73 |
| Agentic & Tools | — | 80 |
| Specifications | ||
| Developer | OpenAI | Moonshot |
| Family | GPT | Kimi |
| Released | Mar 5, 2026 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | API access | Open weights (non-commercial) |
| Context window | 1.1M | 1M |
| Price — $/M input | $30.00 | $2.10 |
| Price — $/M output | $180.00 | $10.95 |
| Inputs | text, image, file | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| ARC-AGI | 95% | 95% |
| ARC-AGI-2 | 83% | 60% |
| FrontierMath | 50% | — |
| FrontierMath Tier 4 | 38% | — |
| GPQA Diamond | 95% | 93% |
| Humanity's Last Exam | 44% | 47% |
| SimpleBench | 74% | 61% |
| SimpleQA Verified | 46% | 51% |
| WeirdML | 57% | 83% |
| AIME 2024/2025 | — | 97% |
| APEX | — | 39% |
| SciCode | — | 60% |
| WebDev Arena | — | 1674 |
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-5.4 Pro better than Kimi K3?
On Epoch AI's Capabilities Index, GPT-5.4 Pro 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-5.4 Pro or Kimi K3?
Kimi K3 is cheaper on input tokens at $2.10 per million, versus $30.00 (representative OpenRouter pricing).
Which has a larger context window, GPT-5.4 Pro or Kimi K3?
GPT-5.4 Pro supports up to 1.1M tokens, compared with 1M 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.