General Intelligence Ranking
See which AI models perform best on General Intelligence, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↓.
319/319
Filter models
No models match the current search and filters.
| Rank | Model | Company | General Intelligence Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #157 | Gemma 4 26B A4B medium | 10.0 | 6.8 | $0.092 | 1/1 | 29.8s | |
| #216 | Seed 2.1 Turbo none | Bytedance Seed | 5.0 | 5.9 | $0.092 | 0/1 | 2.44s |
| #294 | Grok 4.20 Beta none | X AI | 5.0 | 4.4 | $0.087 | 0/1 | 541ms |
| #156 | Gemini 3 Flash Preview none | 10.0 | 6.8 | $0.085 | 1/1 | 1.13s | |
| #290 | Granite 4.2 8B high | IBM Granite | 5.5 | 4.6 | $0.084 | 0/1 | 16.4s |
| #269 | Laguna S 2.1 low | Poolside | 4.8 | 5.0 | $0.082 | 0/1 | 650ms |
| #136 | DeepSeek V3.2 medium | DeepSeek | 3.4 | 7.0 | $0.078 | 0/1 | 58.3s |
| #228 | KAT-Coder-Air V2.5 high | Kwaipilot | 5.1 | 5.6 | $0.077 | 0/1 | 7.10s |
| #208 | Qwen3.5-Flash none | Qwen | 10.0 | 6.0 | $0.073 | 1/1 | 803ms |
| #172 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.4 | 6.6 | $0.073 | 0/1 | 2.26s |
| #69 | DeepSeek V4 Flash 0731 low | DeepSeek | 6.5 | 8.0 | $0.072 | 0/1 | 7.63s |
| #111 | GPT-5.6 Luna medium | OpenAI | 5.1 | 7.4 | $0.072 | 0/1 | 4.34s |
| #77 | Qwen3.8 27B low | Qwen | 5.0 | 7.9 | ~$0.071 | 0/1 | 5.37s |
| #282 | KAT-Coder-Air V2.5 none | Kwaipilot | 5.0 | 4.8 | $0.070 | 0/1 | 12.0s |
| #286 | Grok 4.1 Fast medium | X AI | 4.2 | 4.7 | $0.069 | 0/1 | 16.2s |