GPT-5 Mini vs Kimi K2.5
Head to head on 25 shared benchmarks, with price, context window, and release dates.
Benchmark scores
77evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Kimi K2.5 Moonshot AI | 68.3% | 1579elo | 74.9 | 27.9% | 87.9% | 30.7% | 70.2% | 72.5% | 77.9% | 61.4% | 57.4% | 77.7% | 84.9% | 76.0% | 39.3% | 76.4% | 66.5% | 49.9% | 49.0% | 67.3% | 70.8% | 74.2% | 34.8% | 17.5% | 95.9% | - | - | 96.1 | - | - | - | - | - | - | - | - | 35.0% | - | - | - | - | - | - | 35.8% | - | - | - | - | 95.4 | - | - | 78.5% | 10421 | - | - | - | - | 62.0% | - | 87.1 | - | 63.3% | - | - | - | 73 | - | 69.4 | - | - | - | - | 26.3% | - | - | - | - | 59.8% |
| GPT-5 Mini OpenAI | 60.2% | 1313elo | 56.2 | 27.2% | 82.8% | 21.5% | 75.4% | 69.1% | 68.2% | 55.2% | 65.3% | 75.5% | 82.2% | 68.3% | 43.0% | 80.6% | 66.9% | 43.0% | 39.0% | 39.7% | 59.8% | 75.2% | 33.3% | 14.2% | 68.4% | 0.0% | 90.7% | - | 0.0% | 1.13 | 0.0% | -0.15 | 20.0% | 25.0% | 40.0% | 1.7 | - | 100.0% | 18.1% | 2.8% | 100.0% | 66.7% | 0.0% | - | 88.3% | 60.0% | 100.0% | 90.0% | - | 47.2% | 80.0% | - | - | 83.8% | 0.0% | 1.54 | 1.54 | - | 80.0% | - | 83.7% | - | 9.0% | 16.8% | 4.95 | - | 0.0% | - | 9.5% | 0.0% | 86.1% | 0.49 | - | 39.21 | 272.11 | 86.0% | 86.0% | 51.6% |
2 / 2 models
| Attribute | GPT-5 Mini OpenAI | Kimi K2.5 Moonshot AI |
|---|---|---|
| Description | GPT-5 mini is an AI model from OpenAI. | Kimi K2.5 is an AI model from Kimi. |
| Family | GPT | Kimi |
| Params | - | - |
| Open weights | closed | open |
| License | proprietary | Modified MIT |
| Released | 7 Aug 2025 | 27 Jan 2026 |
| Context | 400,000 | 262,144 |
| Input $/1M | $0.25 | $0.60 |
| Output $/1M | $2.00 | $2.75 |
| Cache read $/1M | $0.025 | $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 | - | - |
| Publisher | OpenAI | Moonshot AI |
| Reported scores | 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 Mini or Kimi K2.5 better?
- Across the 25 benchmarks both models report on Sophon, Kimi K2.5 leads on 19 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-5 Mini and Kimi K2.5 compare on GPQA Diamond?
- GPT-5 Mini scores 82.8% and Kimi K2.5 scores 87.9% on GPQA Diamond.
- Which is cheaper, GPT-5 Mini or Kimi K2.5?
- GPT-5 Mini is cheaper at $2.00 per million output tokens against $2.75 for Kimi K2.5 - about 1.4x.
- When were GPT-5 Mini and Kimi K2.5 released?
- GPT-5 Mini was released 7 Aug 2025 by OpenAI. Kimi K2.5 was released 27 Jan 2026 by Moonshot AI.
Other head-to-heads
56GPT-5 Mini vs GPT-5 Nano38 shared evalsGPT-5 vs GPT-5 Mini36 shared evalsGPT-4.1 Mini vs GPT-5 Mini32 shared evalsGPT-5 Mini vs GPT-5.232 shared evalsClaude Sonnet 4.5 vs GPT-5 Mini31 shared evalsClaude Opus 4.5 vs GPT-5 Mini31 shared evalsClaude Opus 4.6 vs Kimi K2.531 shared evalsGemini 3.1 Pro Preview vs Kimi K2.530 shared evalsClaude 4 Sonnet vs GPT-5 Mini29 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 evalsClaude Opus 4.6 vs GPT-5 Mini28 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 evalsGemini 3.1 Pro Preview vs GPT-5 Mini27 shared evalsGPT-5 Mini vs GPT-5.427 shared evalsClaude Sonnet 4.6 vs Kimi K2.527 shared evalsDeepSeek V3.2 vs GPT-5 Mini26 shared evalsGemini 2.5 Pro vs GPT-5 Mini26 shared evalsGPT-5 Mini vs Grok 4.1 Fast26 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 GPT-5.525 shared evalsGLM 5.1 vs GPT-5 Mini25 shared evalsClaude Opus 4.7 vs GPT-5 Mini25 shared evalsGPT-5 Mini vs gpt-oss-120b25 shared evalsGLM 4.7 vs GPT-5 Mini25 shared evalsDeepSeek V3.2 vs Kimi K2.525 shared evalsGPT-5.4 Mini vs Kimi K2.525 shared evalsClaude Opus 4.8 vs GPT-5 Mini24 shared evalsGPT-5.4 Mini vs GPT-5 Mini24 shared evalsGrok 4.1 Fast vs Kimi K2.524 shared evalsClaude Fable 5 vs GPT-5 Mini23 shared evalsClaude Sonnet 4.6 vs GPT-5 Mini23 shared evalsClaude 4 Sonnet vs Kimi K2.523 shared evalsGPT-4.1 vs GPT-5 Mini22 shared evalsGPT-5 Nano vs Kimi K2.522 shared evalsGPT-4.1 Nano vs GPT-5 Mini21 shared evalsGPT-5 Mini vs Qwen3.6 Plus21 shared evalsGemini 2.5 Pro vs Kimi K2.521 shared evalsGPT-4o vs GPT-5 Mini20 shared evalsGLM 4.7 vs Kimi K2.520 shared evalsgpt-oss-120b vs Kimi K2.519 shared evalsGPT-4o-mini vs GPT-5 Mini18 shared evalsGPT-5 vs Kimi K2.518 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 Mini 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.