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 K3?

127 SI-IQ · 90% interval 124–130
Rank 23 of 80 ranked models · Plausible rank range 13–38

Kimi K3 is a model from Moonshot, released on Jul 16, 2026. Its SI-IQ is 127 (90% interval 124–130), estimated from 9 benchmark results by 2 evaluators.

Data as of Oct 18, 2026 · method 1.0.0

Facts

Developer
Moonshot
Released
Jul 16, 2026
Access
Open weights (non-commercial licence)
Benchmarks used
9 benchmark results from 2 evaluators
API price
$3.00 input / $15 output per 1M tokens (developer's price list, Oct 18, 2026)
Context window
1,048,576 tokens

Ability by area (SI-IQ, 90% interval)

6080100120140160Reasoning124Math128Knowledge130

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 Area Score Implied SI-IQ Evaluated by As listed by the source Retrieved Source
Chess Puzzles Reasoning 37.0% 126 Epoch AI kimi-k3_high Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Furniture Assembly not in index Reasoning 34.2% — Epoch AI kimi-k3_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles Reasoning 26.0% 120 Epoch AI kimi-k3_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4 Math 39.0% 128 Epoch AI kimi-k3_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3 Math 72.2% 129 Epoch AI kimi-k3_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025 Math 97.2% 128 Epoch AI kimi-k3_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond Knowledge 93.1% 132 Epoch AI kimi-k3_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run) Knowledge 91.6% 134 OpenRouter moonshotai/kimi-k3-20260715
Moonshot AI · first-party provider (1 of 14 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file
SimpleQA Verified Knowledge 50.6% 130 Epoch AI kimi-k3_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run) Agents 73.5% 126 OpenRouter moonshotai/kimi-k3-20260715
Moonshot AI · first-party provider (1 of 19 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, Kimi K3 has a rating of 1,487 (1,482–1,492) from 32,795 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

ModelSI-IQ
Muse Spark OpenMeta AI127Kimi K3 vs Muse Spark Open
Claude Opus 4.7Anthropic127Kimi K3 vs Claude Opus 4.7
Gemini 3.1 ProGoogle DeepMind127Kimi K3 vs Gemini 3.1 Pro
DeepSeek V4 Pro 0813DeepSeek128Kimi K3 vs DeepSeek V4 Pro 0813
DeepSeek V4.1 FlashDeepSeek128Kimi K3 vs DeepSeek V4.1 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); 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).