GPT-5 vs Kimi K2.5
Head to head on 18 shared benchmarks, with price, context window, and release dates.
Benchmark scores
81evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 OpenAI | 61.1% | 1627elo | 72.8 | 32.4% | 85.4% | 28.5% | 73.1% | 83.4% | 49.6% | 83.7% | 65.5% | 43.7% | 42.9% | 74.4% | 73.4% | 32.6% | 20.1% | 84.8% | 46.7% | 91.1% | 88.0% | 94.6% | 94.3% | - | 0.0% | 0.15 | 0.0% | 68.1% | 4.58 | - | 57.7% | 80.0% | 80.0% | - | 91.7% | 0.0% | 88.9% | 83.3% | 100.0% | - | 48.9% | - | 58.2% | - | - | - | - | - | - | - | 84.6% | 37.5% | 0.52 | 1.62 | 100.0% | 99.4% | - | 0.0% | 92.7% | 92.7% | 93.3% | 10.0% | - | 87.1% | 0.0% | 60.0% | 0.26 | - | 0.0% | 18.0% | - | 74.9% | - | 2.34 | - | 87.5% | 0.86 | - | 54.8% | 90.0% | 90.0% | 61.9% |
| Kimi K2.5 Moonshot AI | 68.3% | 1579elo | 74.9 | 27.9% | 87.9% | 30.7% | 70.2% | 78.5% | 39.3% | 76.4% | 66.5% | 49.9% | 49.0% | 70.8% | 74.2% | 34.8% | 17.5% | 95.9% | - | - | - | - | - | 96.1 | - | - | - | - | - | 35.0% | - | - | - | 35.8% | - | - | - | - | - | 95.4 | - | 10421 | - | 72.5% | 77.9% | 61.4% | 57.4% | 77.7% | 84.9% | 76.0% | - | - | - | - | - | - | 62.0% | - | - | - | - | - | 87.1 | - | - | - | - | 63.3% | - | - | 73 | - | 67.3% | - | 69.4 | - | - | 26.3% | - | - | - | 59.8% |
2 / 2 models
| Attribute | GPT-5 OpenAI | Kimi K2.5 Moonshot AI |
|---|---|---|
| Description | OpenAI's August 2025 unified frontier model that auto-routes between a fast model and a deeper "thinking" variant. | Kimi K2.5 is an AI model from Kimi. |
| Family | GPT 5 | Kimi |
| Params | Undisclosed (closed) | - |
| Open weights | closed | open |
| License | proprietary | Modified MIT |
| Released | 7 Aug 2025 | 27 Jan 2026 |
| Context | 400,000 | 262,144 |
| Input $/1M | $1.25 | $0.60 |
| Output $/1M | $10.00 | $2.75 |
| Cache read $/1M | $0.125 | $0.150 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image, file | text, image |
| Providers | openai | - |
| Publisher | OpenAI | Moonshot AI |
| Reported scores | SWE-bench74.9% (Verified) GPQA Diamond85.4% (AA) Humanity's Last Exam (HLE)28.5% (AA) IFBench73.1% (AA) | GPQA Diamond87.9% (AA) Humanity's Last Exam (HLE)30.7% (AA) IFBench70.2% (AA) SciCode49.0% (AA) τ²-bench (Tau²-bench)95.9% (AA) |
FAQ
- Is GPT-5 or Kimi K2.5 better?
- Across the 18 benchmarks both models report on Sophon, Kimi K2.5 leads on 10 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-5 and Kimi K2.5 compare on GPQA Diamond?
- GPT-5 scores 85.4% and Kimi K2.5 scores 87.9% on GPQA Diamond.
- Which is cheaper, GPT-5 or Kimi K2.5?
- Kimi K2.5 is cheaper at $2.75 per million output tokens against $10.00 for GPT-5 - about 3.6x.
- When were GPT-5 and Kimi K2.5 released?
- GPT-5 was released 7 Aug 2025 by OpenAI. Kimi K2.5 was released 27 Jan 2026 by Moonshot AI.
Other head-to-heads
56GPT-4.1 Mini vs GPT-541 shared evalsGPT-5 vs GPT-5 Mini36 shared evalsClaude Sonnet 4.5 vs GPT-531 shared evalsClaude Opus 4.6 vs Kimi K2.531 shared evalsGemini 3.1 Pro Preview vs Kimi K2.530 shared evalsGPT-5.2 vs Kimi K2.529 shared evalsKimi K2.5 vs Qwen3.6 Plus29 shared evalsClaude Sonnet 4.5 vs Kimi K2.528 shared evalsGPT-5 vs GPT-5 Nano28 shared evalsGPT-4.1 vs GPT-528 shared evalsGPT-5.5 vs Kimi K2.528 shared evalsClaude Opus 4.8 vs Kimi K2.528 shared evalsGPT-5.4 vs Kimi K2.528 shared evalsClaude Opus 4.7 vs Kimi K2.528 shared evalsClaude Sonnet 4.6 vs Kimi K2.527 shared evalsClaude Opus 4.5 vs Kimi K2.526 shared evalsClaude Fable 5 vs Kimi K2.526 shared evalsGLM 5.1 vs Kimi K2.526 shared evalsGPT-5 Mini vs Kimi K2.525 shared evalsClaude 4 Sonnet vs GPT-525 shared evalsDeepSeek V3.2 vs Kimi K2.525 shared evalsGPT-5.4 Mini vs Kimi K2.525 shared evalsGemini 2.5 Pro vs GPT-524 shared evalsGrok 4.1 Fast vs Kimi K2.524 shared evalsGPT-5 vs GPT-5.223 shared evalsClaude Opus 4.5 vs GPT-523 shared evalsClaude 4 Sonnet vs Kimi K2.523 shared evalsGPT-5 Nano vs Kimi K2.522 shared evalsGPT-4.1 Nano vs GPT-521 shared evalsGemini 2.5 Pro vs Kimi K2.521 shared evalsGPT-5 vs Grok 4.1 Fast20 shared evalsGLM 4.7 vs Kimi K2.520 shared evalsGemini 3.1 Pro Preview vs GPT-519 shared evalsClaude Opus 4.6 vs GPT-519 shared evalsGPT-5 vs GPT-5.419 shared evalsDeepSeek V3.2 vs GPT-519 shared evalsGPT-4o vs GPT-519 shared evalsgpt-oss-120b vs Kimi K2.519 shared evalsGPT-5 vs GPT-5.518 shared evalsClaude Opus 4.8 vs GPT-517 shared evalsClaude Opus 4.7 vs GPT-517 shared evalsGPT-5 vs gpt-oss-120b17 shared evalsGLM 4.7 vs GPT-517 shared evalsClaude Fable 5 vs GPT-516 shared evalsGPT-4o-mini vs GPT-516 shared evalsClaude Sonnet 4.6 vs GPT-516 shared evalsGLM 5.1 vs GPT-516 shared evalsGPT-5 vs GPT-5.4 Mini16 shared evalsGPT-5 vs Qwen3.6 Plus15 shared evalsGPT-4o vs Kimi K2.515 shared evalsGPT-6 Astra vs Kimi K2.513 shared evalsGPT-4.1 Mini vs Kimi K2.512 shared evalsGPT-5 vs GPT-6 Astra12 shared evalsGPT-4.1 vs Kimi K2.512 shared evalsGPT-4o-mini vs Kimi K2.512 shared evalsGPT-4.1 Nano vs Kimi K2.512 shared evals
Comparing something else? Build your own side-by-side.