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 K2.6?
Kimi K2.6 is a model from Moonshot, released on Apr 20, 2026. Its SI-IQ is 121 (90% interval 118–124), estimated from 9 benchmark results by 2 independent evaluators. Its strongest area is Math and its weakest is Reasoning.
Facts
- Developer
- Moonshot
- Released
- Apr 20, 2026
- Access
- Open weights (restricted licence)
- Benchmarks used
- 9 results from 2 evaluators
- API price
- $0.95 input / $4.00 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 |
|---|---|---|---|
| Chess Puzzles | 20.0% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| Furniture Assembly not in index | 21.7% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| Mystery Game Puzzles | 18.0% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| FrontierMath Tier 4 | 25.6% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| FrontierMath Tiers 1–3 | 57.2% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| OTIS Mock AIME 2024–2025 | 96.1% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| SWE-bench Verified (Epoch AI run) | 76.7% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| GPQA Diamond | 90.8% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| GPQA Diamond (OpenRouter run) | 88.0% | OpenRouter | OpenRouter benchmark datasets · data file |
| SimpleQA Verified | 34.9% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| τ²-bench Airline (OpenRouter run) | 76.7% | OpenRouter | OpenRouter benchmark datasets · data file |
Human preference (Arena)
On the Arena leaderboard, where people vote between two anonymous answers, Kimi K2.6 has a rating of 1,461 (1,456–1,465) from 40,013 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)
Models with similar SI-IQ
| Model | SI-IQ | |
|---|---|---|
| GPT-5OpenAI | 121 | Kimi K2.6 vs GPT-5 |
| GLM-5.2Z.ai (Zhipu AI) | 121 | Kimi K2.6 vs GLM-5.2 |
| GLM-5.3-FlashZ.ai (Zhipu AI) | 120 | Kimi K2.6 vs GLM-5.3-Flash |
| GPT-5.1OpenAI | 120 | Kimi K2.6 vs GPT-5.1 |
| Gemini 3 FlashGoogle DeepMind | 122 | Kimi K2.6 vs Gemini 3 Flash |
Computed with SI-IQ method version 1.0.0. Read the full methodology
Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..