# Best AI Models in Kilo

> Live rankings of AI coding models from real Kilo Code usage across 5M+ developers. HTML: https://kilo.ai/leaderboard

Generated: 2026-10-19

## Methodology

Models earn their rank from the developers using them, not from a spec sheet. Rankings use real token usage across 500+ hosted models and update about every 5 minutes.

## Featured coding models

1. GPT-5.6 Sol — 76.2% KiloBench completion — A flagship model for long-horizon agents and complex problem solving
   Model: https://kilo.ai/models/openai-gpt-5-6-sol
   Read more: https://blog.kilo.ai/p/the-new-gpt-56-models-will-blow-your

2. Claude Opus 4.8 — 74.3 Coding Index — Built for complex planning, orchestration, and long-running professional tasks
   Model: https://kilo.ai/models/anthropic-claude-opus-4-8
   Read more: https://blog.kilo.ai/p/we-audited-the-same-codebase-with

3. Grok 4.6 — 73.0% KiloBench completion — Frontier coding and STEM performance tuned for long-running agents
   Model: https://kilo.ai/models/x-ai-grok-4-6
   Read more: https://x.ai/news/grok-4-6

4. Step 3.7 Flash — 256k context window — A fast, open-weight model designed for efficient agentic workflows
   Read more: https://blog.kilo.ai/p/new-models-from-stepfun-and-minimax

## KiloBench (Terminal Bench 2.0)

Cost vs performance across the best coding models. Source: https://www.tbench.ai/

| Rank | Model | Completion | Cost per attempt | URL |
| --- | --- | --- | --- | --- |
| 1 | GPT-6 Astra ($$$$) | 79.3% | $107.29 | https://kilo.ai/models/openai-gpt-6-astra |
| 2 | GPT-5.6 Sol | 76.2% | $87.41 | https://kilo.ai/models/openai-gpt-5-6-sol |
| 3 | Claude Fable 5.1 ($$$$) | 76.2% | $91.41 | https://kilo.ai/models/anthropic-claude-fable-5-1 |
| 4 | DeepSeek V4.1 Flash | 75.3% | $2.58 | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 5 | Gemini 3.8 Flash (50% off) | 75.3% | $112.27 | https://kilo.ai/models/google-gemini-3-8-flash |
| 6 | GPT-5.5 | 74.2% | $72.63 | https://kilo.ai/models/openai-gpt-5-5 |
| 7 | Grok 4.6 | 73.0% | $33.83 | https://kilo.ai/models/x-ai-grok-4-6 |
| 8 | Kimi K3 | 72.8% | $48.38 | https://kilo.ai/models/moonshotai-kimi-k3 |
| 9 | Claude Opus 5 | 71.5% | $113.54 | https://kilo.ai/models/anthropic-claude-opus-5 |
| 10 | Claude Fable 5 ($$$$) | 71.0% | $87.52 | https://kilo.ai/models/anthropic-claude-fable-5 |

## Top models by agent

### Code

| Rank | Model | Share | URL |
| --- | --- | --- | --- |
| 1 | step-5-preview-free | 26.3% |  |
| 2 | NVIDIA: Nemotron 3 Ultra | 14.3% | https://kilo.ai/models/nvidia-nemotron-3-ultra-550b-a55b |
| 3 | Poolside: Laguna S 2.1 (free) | 11.2% | https://kilo.ai/models/poolside-laguna-s-2-1-free |
| 4 | NVIDIA: Nemotron 3.5 Super VL (free) | 10.4% | https://kilo.ai/models/nvidia-nemotron-3-5-super-vl-free |
| 5 | glyph-cluster | 7.6% |  |
| 6 | DeepSeek: DeepSeek V4.1 Flash | 5.8% | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 7 | Dots Studio: Dots3-Note Preview (free) | 4.8% | https://kilo.ai/models/dots-studio-dots-3-note-preview-free |
| 8 | NVIDIA: Nemotron 3 Super (free) | 4.8% | https://kilo.ai/models/nvidia-nemotron-3-super-120b-a12b-free |
| 9 | Z.ai: GLM 5.3 Flash | 1.2% | https://kilo.ai/models/z-ai-glm-5-3-flash |
| 10 | inclusionAI: Ling 3.1 Flash | 1.0% | https://kilo.ai/models/inclusionai-ling-3-1-flash |

### Plan

| Rank | Model | Share | URL |
| --- | --- | --- | --- |
| 1 | step-5-preview-free | 20.4% |  |
| 2 | NVIDIA: Nemotron 3 Ultra | 13.3% | https://kilo.ai/models/nvidia-nemotron-3-ultra-550b-a55b |
| 3 | Poolside: Laguna S 2.1 (free) | 11.0% | https://kilo.ai/models/poolside-laguna-s-2-1-free |
| 4 | DeepSeek: DeepSeek V4.1 Flash | 8.8% | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 5 | glyph-cluster | 6.8% |  |
| 6 | NVIDIA: Nemotron 3.5 Super VL (free) | 6.3% | https://kilo.ai/models/nvidia-nemotron-3-5-super-vl-free |
| 7 | Dots Studio: Dots3-Note Preview (free) | 6.2% | https://kilo.ai/models/dots-studio-dots-3-note-preview-free |
| 8 | Anthropic: Claude Opus 5.5 | 3.5% | https://kilo.ai/models/anthropic-claude-opus-5-5 |
| 9 | NVIDIA: Nemotron 3 Super (free) | 3.3% | https://kilo.ai/models/nvidia-nemotron-3-super-120b-a12b-free |
| 10 | beam-free | 1.4% |  |

### Ask

| Rank | Model | Share | URL |
| --- | --- | --- | --- |
| 1 | NVIDIA: Nemotron 3 Ultra | 16.6% | https://kilo.ai/models/nvidia-nemotron-3-ultra-550b-a55b |
| 2 | step-5-preview-free | 14.6% |  |
| 3 | Poolside: Laguna S 2.1 (free) | 10.2% | https://kilo.ai/models/poolside-laguna-s-2-1-free |
| 4 | glyph-cluster | 10.0% |  |
| 5 | NVIDIA: Nemotron 3.5 Super VL (free) | 7.8% | https://kilo.ai/models/nvidia-nemotron-3-5-super-vl-free |
| 6 | Dots Studio: Dots3-Note Preview (free) | 7.3% | https://kilo.ai/models/dots-studio-dots-3-note-preview-free |
| 7 | DeepSeek: DeepSeek V4.1 Flash | 5.9% | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 8 | Anthropic: Claude Opus 5.5 | 3.3% | https://kilo.ai/models/anthropic-claude-opus-5-5 |
| 9 | NVIDIA: Nemotron 3 Super (free) | 3.2% | https://kilo.ai/models/nvidia-nemotron-3-super-120b-a12b-free |
| 10 | Z.ai: GLM 5.3 Flash | 2.4% | https://kilo.ai/models/z-ai-glm-5-3-flash |

### Debug

| Rank | Model | Share | URL |
| --- | --- | --- | --- |
| 1 | step-5-preview-free | 28.1% |  |
| 2 | NVIDIA: Nemotron 3 Ultra | 17.8% | https://kilo.ai/models/nvidia-nemotron-3-ultra-550b-a55b |
| 3 | NVIDIA: Nemotron 3.5 Super VL (free) | 11.0% | https://kilo.ai/models/nvidia-nemotron-3-5-super-vl-free |
| 4 | Poolside: Laguna S 2.1 (free) | 10.1% | https://kilo.ai/models/poolside-laguna-s-2-1-free |
| 5 | glyph-cluster | 8.3% |  |
| 6 | Dots Studio: Dots3-Note Preview (free) | 4.1% | https://kilo.ai/models/dots-studio-dots-3-note-preview-free |
| 7 | DeepSeek: DeepSeek V4.1 Flash | 3.9% | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 8 | NVIDIA: Nemotron 3 Super (free) | 2.7% | https://kilo.ai/models/nvidia-nemotron-3-super-120b-a12b-free |
| 9 | muse-spark-1.3-contributor | 1.9% |  |
| 10 | free | 1.2% |  |

### Review

| Rank | Model | Share | URL |
| --- | --- | --- | --- |
| 1 | DeepSeek: DeepSeek V4.1 Flash | 20.4% | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 2 | step-5-preview-free | 9.3% |  |
| 3 | NVIDIA: Nemotron 3 Ultra | 8.0% | https://kilo.ai/models/nvidia-nemotron-3-ultra-550b-a55b |
| 4 | Anthropic: Claude Opus 5.5 | 7.9% | https://kilo.ai/models/anthropic-claude-opus-5-5 |
| 5 | Z.ai: GLM 5.3 Flash | 6.7% | https://kilo.ai/models/z-ai-glm-5-3-flash |
| 6 | glyph-cluster | 6.2% |  |
| 7 | NVIDIA: Nemotron 3.5 Super VL (free) | 5.2% | https://kilo.ai/models/nvidia-nemotron-3-5-super-vl-free |
| 8 | Dots Studio: Dots3-Note Preview (free) | 3.4% | https://kilo.ai/models/dots-studio-dots-3-note-preview-free |
| 9 | OpenAI: GPT-6.1 Sol | 2.7% | https://kilo.ai/models/openai-gpt-6-1-sol |
| 10 | Google: Gemini 3.8 Flash (50% off) | 2.5% | https://kilo.ai/models/google-gemini-3-8-flash |

### kiloclaw

| Rank | Model | Share | URL |
| --- | --- | --- | --- |
| 1 | muse-spark-1.3-contributor | 23.2% |  |
| 2 | Xiaomi: MiMo-V2.5-Pro (retires Oct 21) | 17.3% | https://kilo.ai/models/xiaomi-mimo-v2-5-pro |
| 3 | DeepSeek: DeepSeek V4.1 Flash | 8.2% | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 4 | NVIDIA: Nemotron 3 Ultra | 8.2% | https://kilo.ai/models/nvidia-nemotron-3-ultra-550b-a55b |
| 5 | glyph-cluster | 7.7% |  |
| 6 | Dots Studio: Dots3-Note Preview (free) | 4.9% | https://kilo.ai/models/dots-studio-dots-3-note-preview-free |
| 7 | MiniMax: MiniMax M3 (free) | 4.6% | https://kilo.ai/models/minimax-minimax-m3-free |
| 8 | NVIDIA: Nemotron 3 Super (free) | 4.6% | https://kilo.ai/models/nvidia-nemotron-3-super-120b-a12b-free |
| 9 | NVIDIA: Nemotron 3.5 Super VL (free) | 4.0% | https://kilo.ai/models/nvidia-nemotron-3-5-super-vl-free |
| 10 | Anthropic: Claude Opus 5.5 | 2.8% | https://kilo.ai/models/anthropic-claude-opus-5-5 |

## Top models today

Most-used models across Kilo Code in the last 24 hours.

| Rank | Model | Tokens (24h) | URL |
| --- | --- | --- | --- |
| 1 | NVIDIA: Nemotron 3.5 Super VL (free) | 150.9B | https://kilo.ai/models/nvidia-nemotron-3-5-super-vl-free |
| 2 | NVIDIA: Nemotron 3 Ultra | 109.1B | https://kilo.ai/models/nvidia-nemotron-3-ultra-550b-a55b |
| 3 | Dots Studio: Dots3-Note Preview (free) | 75.8B | https://kilo.ai/models/dots-studio-dots-3-note-preview-free |
| 4 | Poolside: Laguna S 2.1 (free) | 70.0B | https://kilo.ai/models/poolside-laguna-s-2-1-free |
| 5 | glyph-cluster | 57.7B |  |
| 6 | beam-free | 50.4B |  |
| 7 | DeepSeek: DeepSeek V4.1 Flash | 26.9B | https://kilo.ai/models/deepseek-deepseek-v4-1-flash |
| 8 | NVIDIA: Nemotron 3 Super (free) | 25.1B | https://kilo.ai/models/nvidia-nemotron-3-super-120b-a12b-free |
| 9 | deepseek-flash-latest | 19.5B |  |
| 10 | deepseek-v4.1-flash-1017 | 16.7B |  |

## How to read the leaderboard

1. Start with usage — The rankings reflect real token usage by Kilo Code developers, not synthetic benchmarks.
2. Filter by agent — Use the Top Models by Agent section to see which models lead in Code, Plan, Debug, and Ask, alongside historical Orchestrator usage.
3. Open the model page — Each model links to a dedicated page with benchmark scores, pricing, context length, and speed data.
4. Switch in Kilo Code — All 500+ models are available in Kilo Code. Switch from the model selector at any time.

## FAQ

### What is the Kilo Code AI Model Leaderboard?

The Kilo Code leaderboard shows live rankings of AI coding models based on real token usage by 5M+ developers. Rankings reflect genuine developer preference and update every 5 minutes.

### How are AI coding models ranked?

Models are ranked by total token usage from Kilo Code developers. The ranking reflects real-world developer preference and can be filtered by agents such as Code, Plan, Debug, and Ask, alongside historical Orchestrator usage.

### Which AI model is best for coding?

The current top-ranked model is NVIDIA: Nemotron 3.5 Super VL (free), based on real developer usage. The best AI model for your workflow can vary by coding, planning, debugging, and agent tasks, so compare the live rankings by agent before choosing.

### How often does the leaderboard update?

The leaderboard updates every 5 minutes with fresh usage data from real Kilo Code developers.

## Related

- Compare models: https://kilo.ai/models/compare
- Open source models: https://kilo.ai/open-source-models
- Browse by lab: https://kilo.ai/models/by
- KiloBench methodology: https://kilo.ai/kilobench
- KiloBench capability tier list: https://kilo.ai/leaderboard/tier-list
- Inference: https://kilo.ai/leaderboard/inference
- Provider race: https://kilo.ai/leaderboard/race
- PinchBench: https://pinchbench.com
- HTML leaderboard: https://kilo.ai/leaderboard
- This file: https://kilo.ai/leaderboard/llm.txt