AGENTKERNEL
- Home
- Leaderboard
- Overall
Overall: the best AI models in October 2026
As of Oct 09, 2026, Claude Opus 5.5 leads the “Overall” ranking, ahead of Claude Sonnet 5.5 and Claude Fable 5.1.
Best model with open weights: MiMo-V2.6-Pro (46.3).
Cheapest strong option: Claude Sonnet 5.5 with 56 points, at most five points behind the leader, for $4.50 a month at 1M input and 250,000 output tokens.
Open in the interactive comparisonOverall 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 Opus 5.5Anthropic | Proprietary | 57.6 | $4.00 / $20.00 |
| 2 | Claude Sonnet 5.5Anthropic | Proprietary | 56 | $2.00 / $10.00 |
| 3 | Claude Fable 5.1Anthropic | Proprietary | 53.4 | $10.00 / $50.00 |
| 4 | GPT-6 AstraOpenAI | Proprietary | 52.7 | $10.00 / $50.00 |
| 5 | GPT-6.1 SolOpenAI | Proprietary | 51.8 | $2.00 / $10.00 |
| 6 | Claude Opus 5Anthropic | Proprietary | 50.8 | $5.00 / $25.00 |
| 7 | Claude Fable 5Anthropic | Proprietary | 49.6 | $10.00 / $50.00 |
| 8 | Muse Spark 1.3Meta | Proprietary | 48.1 | $1.25 / $4.25 |
| 9 | GPT-6 SolOpenAI | Proprietary | 47.6 | $2.00 / $10.00 |
| 10 | GPT-5.6 SolOpenAI | Proprietary | 47 | $2.00 / $10.00 |
| 11 | Grok 4.7xAI | Proprietary | 46.4 | $2.00 / $6.00 |
| 12 | MiMo-V2.6-ProXiaomi | Open | 46.3 | $0.435 / $0.87 |
| 13 | Qwen3.8 Max (0902)Qwen | Proprietary | 45.4 | $2.00 / $6.00 |
| 14 | GLM 5.3Z.ai | Open | 44.8 | $0.04 / $7.00 |
| 15 | Grok 4.6xAI | Proprietary | 44.3 | $2.00 / $6.00 |