AGENTKERNEL
- Home
- Leaderboard
- Coding
Coding: the best AI models in October 2026
As of Oct 09, 2026, Claude Fable 5.1 leads the “Coding” ranking, ahead of Claude Opus 5 and GPT-5.6 Sol.
Best model with open weights: Kimi K3 (76.2).
Cheapest strong option: Grok 4.6 with 76.8 points, at most five points behind the leader, for $3.50 a month at 1M input and 250,000 output tokens.
Open in the interactive comparisonCoding ranking
Index points, not a percentage. A gap of one or two points is hardly noticeable in everyday use.
| Rank | Model | Licence | Points | Input / output per 1M |
|---|---|---|---|---|
| 1 | Claude Fable 5.1Anthropic | Proprietary | 81.6 | $10.00 / $50.00 |
| 2 | Claude Opus 5Anthropic | Proprietary | 78 | $5.00 / $25.00 |
| 3 | GPT-5.6 SolOpenAI | Proprietary | 77.4 | $2.00 / $10.00 |
| 4 | GPT-6 AstraOpenAI | Proprietary | 76.9 | $10.00 / $50.00 |
| 5 | Grok 4.6xAI | Proprietary | 76.8 | $2.00 / $6.00 |
| 6 | GPT-5.6 TerraOpenAI | Proprietary | 76.7 | $2.00 / $12.00 |
| 7 | Claude Fable 5Anthropic | Proprietary | 76.5 | $10.00 / $50.00 |
| 8 | Gemini 3.8 FlashGoogle | Proprietary | 76.3 | $0.75 / $3.75 |
| 9 | Kimi K3Moonshot AI | Open | 76.2 | $0.82 / $13.50 |
| 10 | Qwen3.8 Max (0902)Qwen | Proprietary | 76.2 | $2.00 / $6.00 |
| 11 | Muse Spark 1.3Meta | Proprietary | 75.8 | $1.25 / $4.25 |
| 12 | GPT-5.5OpenAI | Proprietary | 74.9 | $5.00 / $30.00 |
| 13 | GLM 5.3Z.ai | Open | 74.8 | $0.04 / $7.00 |
| 14 | Claude Opus 4.8Anthropic | Proprietary | 74.3 | $5.00 / $25.00 |
| 15 | Claude Opus 4.7Anthropic | Proprietary | 73.6 | $5.00 / $25.00 |