Gemini 3.1 Pro Preview vs Kimi K2.5
Head to head on 30 shared benchmarks, with price, context window, and release dates.
Benchmark scores
55evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.1 Pro Preview Google (Alphabet Inc.) | 64.5% | 22.0% | 1489elo | 68.2 | 43.0% | 36.9% | 94.1% | 47.0% | 77.1% | 84.4% | 82.4% | 76.5% | 78.5% | 79.1% | 85.4% | 91.0% | 84.0% | 86.3% | 59.1% | 76.1% | 69.4% | 76.2% | 48.7% | 58.9% | 72.9% | 53.8% | 79.4 | 41.9% | 32.0% | 95.6% | - | 76.8% | 12.3% | 26.5% | 2 | 73.1% | 22.8% | 1142elo | 42.5% | 16.7% | 1314elo | 93.2% | 15.1% | - | - | 0.0% | - | 26.0% | 72.7% | - | - | - | 54.2% | 70.7% | 56.1% | 58.9% |
| Kimi K2.5 Moonshot AI | 68.3% | 39.0% | 1576elo | 74.9 | 35.8% | 27.9% | 78.9% | 13.2% | 43.7% | 78.5% | 72.5% | 77.9% | 61.4% | 57.4% | 77.7% | 84.9% | 76.0% | 62.0% | 39.3% | 76.4% | 66.5% | 63.3% | 49.9% | 39.6% | 74.2% | 18.9% | 69.4 | 26.3% | 17.5% | 81.3% | 96.1 | - | - | - | - | - | - | - | - | - | - | - | - | 95.4 | 10421 | - | 87.1 | - | - | 73 | 67.3% | 70.8% | - | - | - | 56.8% |
2 / 2 models
| Attribute | Gemini 3.1 Pro Preview Google (Alphabet Inc.) | Kimi K2.5 Moonshot AI |
|---|---|---|
| Description | Gemini 3.1 Pro Preview is an AI model from Google (Alphabet Inc.). | Kimi K2.5 is an AI model from Kimi. |
| Family | Gemini | Kimi |
| Params | - | - |
| Open weights | - | closed |
| License | - | Modified MIT |
| Released | 19 Feb 2026 | 27 Jan 2026 |
| Context | 1,048,576 | 262,144 |
| Input $/1M | $2.00 | $0.60 |
| Output $/1M | $12.00 | $3.00 |
| Cache read $/1M | $0.200 | $0.100 |
| Cache write $/1M | $0.375 | - |
| Speed | 122 tok/s | 0 tok/s |
| Latency | 20.68 s | 0.00 s |
| Modalities | audio, file, image, text, video | text, image |
| Providers | - | - |
| Publisher | Google (Alphabet Inc.) | Moonshot AI |
| Reported scores | GPQA Diamond94.1% (AA) Humanity's Last Exam (HLE)47.0% (AA) IFBench77.1% (AA) SciCode58.9% (AA) τ²-bench (Tau²-bench)95.6% (AA) | 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 Gemini 3.1 Pro Preview or Kimi K2.5 better?
- Across the 30 benchmarks both models report on Sophon, Gemini 3.1 Pro Preview leads on 22 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Gemini 3.1 Pro Preview and Kimi K2.5 compare on GPQA Diamond?
- Gemini 3.1 Pro Preview scores 94.1% and Kimi K2.5 scores 78.9% on GPQA Diamond.
- Which is cheaper, Gemini 3.1 Pro Preview or Kimi K2.5?
- Kimi K2.5 is cheaper at $3.00 per million output tokens against $12.00 for Gemini 3.1 Pro Preview - about 4.0x.
- When were Gemini 3.1 Pro Preview and Kimi K2.5 released?
- Gemini 3.1 Pro Preview was released 19 Feb 2026 by Google (Alphabet Inc.). Kimi K2.5 was released 27 Jan 2026 by Moonshot AI.
Comparing something else? Build your own side-by-side.