Themed ranking
Best for coding
Ranked by real coding-task usage share, weighted across nine real OpenRouter coding tags (file I/O, debugging, code review, and more).
As of November 7, 2026, DeepSeek: DeepSeek V4.1 Flash (batch) ranks #1 for best for coding at coding traffic share 53.7%.
- #1 DeepSeek: DeepSeek V4.1 Flash (batch) - Coding traffic share 53.7%
- #2 Z.ai: GLM 5.3 Flash (batch) - Coding traffic share 12.8%
- #3 OpenAI: GPT-6 Luna (batch) - Coding traffic share 6.0%
- #4 OpenAI: GPT-6.1 Sol (batch) - Coding traffic share 5.0%
- #5 Crouton Alpha - Coding traffic share 4.8%
- #6 Tencent: Hy4 preview - Coding traffic share 2.6%
- #7 Xiaomi: MiMo-V2.6-Flash - Coding traffic share 2.6%
- #8 Z.ai: GLM 5.3 (batch) - Coding traffic share 1.8%
- #9 MoonshotAI: Kimi K3.1 Pro - Coding traffic share 1.7%
- #10 MiniMax: MiniMax M3.1 Flash - Coding traffic share 1.5%
| # | Model | Coding traffic share |
|---|---|---|
| 01 | DeepSeek: DeepSeek V4.1 Flash (batch) | 53.7% |
| 02 | Z.ai: GLM 5.3 Flash (batch) | 12.8% |
| 03 | OpenAI: GPT-6 Luna (batch) | 6.0% |
| 04 | OpenAI: GPT-6.1 Sol (batch) | 5.0% |
| 05 | Crouton Alpha | 4.8% |
| 06 | Tencent: Hy4 preview | 2.6% |
| 07 | Xiaomi: MiMo-V2.6-Flash | 2.6% |
| 08 | Z.ai: GLM 5.3 (batch) | 1.8% |
| 09 | MoonshotAI: Kimi K3.1 Pro | 1.7% |
| 10 | MiniMax: MiniMax M3.1 Flash | 1.5% |
| 11 | OpenAI: GPT-5.6 Luna (batch) | 1.5% |
| 12 | Meta: Muse Spark 1.3 Contributor | 1.3% |
| 13 | Tencent: Hy4 | 1.1% |
| 14 | DeepSeek: DeepSeek V4 Flash 0423 | 0.9% |
| 15 | Tencent: Hy3 | 0.9% |
| 16 | NVIDIA: Nemotron 3.5 Super VL (free) | 0.6% |
| 17 | Anthropic: Claude Opus 5.5 (batch) | 0.5% |
| 18 | NVIDIA: Nemotron 3.5 Lightning (free) | 0.2% |
| 19 | Z.ai: GLM 5.2 | 0.2% |
| 20 | Anthropic: Claude Haiku 5.5 (batch) | 0.1% |
| 21 | NVIDIA: Nemotron 3 Ultra (free) | 0.0% |
| 22 | Thinking Machines: Inkling | 0.0% |
| 23 | Anthropic: Claude Sonnet 5.5 (batch) | 0.0% |
Source: OpenRouter (openrouter.ai/rankings), as of November 7, 2026.
Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).
Methodology: www.smophy.ai/benchmark/methodology
Token counts originate from each provider's own tokenizer and are not directly comparable across providers.