GPT-5.4 vs Kimi K2.5
Head to head on 28 shared benchmarks, with price, context window, and release dates.
Benchmark scores
48evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.4 OpenAI | 65.3% | 81.0% | 1836elo | 78.3 | 47.6% | 74.8% | 11.3% | 48.4% | 78.5% | 92063 | 82.0% | 77.5% | 79.3% | 70.2% | 82.6% | 94.1% | 88.1% | 82.8% | 41.3% | 77.5% | 68.3% | 43.3% | 47.1% | 74.0% | 37.9% | 80 | 67.4% | 36.0% | - | 13.1% | 1.47 | 34.1% | 9.0% | 1272elo | - | 87.2% | - | - | 86 | 52.2% | - | 56.0% | -0.61 | 40.8 | - | - | - | - | 60.3% |
| Kimi K2.5 Moonshot AI | 68.3% | 39.0% | 1576elo | 74.9 | 27.9% | 78.9% | 13.2% | 43.7% | 78.5% | 10421 | 72.5% | 77.9% | 61.4% | 57.4% | 77.7% | 84.9% | 76.0% | 62.0% | 39.3% | 76.4% | 66.5% | 49.9% | 39.6% | 74.2% | 18.9% | 69.4 | 17.5% | 81.3% | 96.1 | - | - | - | - | - | 35.8% | - | 95.4 | 87.1 | - | - | 63.3% | - | - | - | 73 | 67.3% | 70.8% | 26.3% | 56.8% |
2 / 2 models
| Attribute | GPT-5.4 OpenAI | Kimi K2.5 Moonshot AI |
|---|---|---|
| Description | GPT-5.4 is an AI model from OpenAI. | Kimi K2.5 is an AI model from Kimi. |
| Family | GPT | Kimi |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | Modified MIT |
| Released | 5 Mar 2026 | 27 Jan 2026 |
| Context | 1,050,000 | 262,144 |
| Input $/1M | $2.50 | $0.60 |
| Output $/1M | $15.00 | $3.00 |
| Cache read $/1M | $0.250 | $0.100 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image, file | text, image |
| Providers | - | - |
| Publisher | OpenAI | Moonshot AI |
| Reported scores | GPQA Diamond74.8% (AA) SciCode47.1% (AA) τ²-bench (Tau²-bench)36.0% (AA) Terminal-Bench (Hard)37.9% (AA) Vibe Code Bench v1.167.4% | GPQA Diamond78.9% (AA) Humanity's Last Exam (HLE)13.2% (AA) IFBench43.7% (AA) SciCode39.6% (AA) τ²-bench (Tau²-bench)81.3% (AA) |
FAQ
- Is GPT-5.4 or Kimi K2.5 better?
- Across the 28 benchmarks both models report on Sophon, GPT-5.4 leads on 21 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-5.4 and Kimi K2.5 compare on GPQA Diamond?
- GPT-5.4 scores 74.8% and Kimi K2.5 scores 78.9% on GPQA Diamond.
- Which is cheaper, GPT-5.4 or Kimi K2.5?
- Kimi K2.5 is cheaper at $3.00 per million output tokens against $15.00 for GPT-5.4 - about 5.0x.
- When were GPT-5.4 and Kimi K2.5 released?
- GPT-5.4 was released 5 Mar 2026 by OpenAI. Kimi K2.5 was released 27 Jan 2026 by Moonshot AI.
Comparing something else? Build your own side-by-side.