Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
How smart is Kimi K2.5?
Kimi K2.5 is a model from Moonshot, released on Jan 27, 2026. Its SI-IQ is 119 (90% interval 112–125), estimated from 6 benchmark results by 2 evaluators.
Data as of Oct 18, 2026 · method 1.0.0
Facts
- Developer
- Moonshot
- Released
- Jan 27, 2026
- Access
- Open weights (restricted licence)
- Benchmarks used
- 6 benchmark results from 2 evaluators
- API price
- $0.60 input / $3.00 output per 1M tokens (developer's price list, Oct 18, 2026)
- Context window
- 262,144 tokens
Ability by area (SI-IQ, 90% interval)
Every benchmark result we used
Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.
| Benchmark | Score | Evaluated by | Source |
|---|---|---|---|
| OTIS Mock AIME 2024–2025 | 92.2% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| SWE-bench Verified (Epoch AI run) | 73.8% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| GPQA Diamond | 87.6% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| GPQA Diamond (OpenRouter run) | 85.9% | OpenRouter | OpenRouter benchmark datasets · data file |
| SimpleQA Verified | 34.3% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| τ²-bench Airline (OpenRouter run) | 72.8% | OpenRouter | OpenRouter benchmark datasets · data file |
Models with similar SI-IQ
| Model | SI-IQ | |
|---|---|---|
| Kimi K2.7 CodeMoonshot | 118 | Kimi K2.5 vs Kimi K2.7 Code |
| Inkling-SmallThinking Machines | 118 | Kimi K2.5 vs Inkling-Small |
| GPT-5.4 NanoOpenAI | 118 | Kimi K2.5 vs GPT-5.4 Nano |
| GPT-5.1OpenAI | 120 | Kimi K2.5 vs GPT-5.1 |
| GLM-5.3-FlashZ.ai (Zhipu AI) | 120 | Kimi K2.5 vs GLM-5.3-Flash |
Computed with SI-IQ method version 1.0.0. Read the full methodology
Data sources: Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); LiteLLM, model_prices_and_context_window.json (MIT); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).