| DeepSeek V4 Pro (Reasoning, Max Effort) | 51.5 | 38.1 | $2.17 |
| DeepSeek V4 Pro (Reasoning, High Effort) | 49.8 | 37.3 | $2.17 |
| DeepSeek V4 Flash (Reasoning, Max Effort) | 46.5 | 80.4 | $0.17 |
| DeepSeek V4 Flash (Reasoning, High Effort) | 44.9 | 0.0 | $0.17 |
| DeepSeek V3.2 (Reasoning) | 41.7 | 78.7 | $0.32 |
| DeepSeek V3.1 Terminus (Reasoning) | 33.9 | 0.0 | $1.91 |
| DeepSeek V3.2 Exp (Reasoning) | 32.9 | 80.0 | $0.32 |
| DeepSeek V3.2 (Non-reasoning) | 32.1 | 78.8 | $0.32 |
| DeepSeek V3.2 Speciale | 29.4 | 0.0 | Free |
| DeepSeek V3.1 Terminus (Non-reasoning) | 28.5 | 0.0 | $0.45 |
| DeepSeek V3.2 Exp (Non-reasoning) | 28.4 | 79.7 | $0.32 |
| DeepSeek V3.1 (Non-reasoning) | 28.1 | 0.0 | $0.83 |
| DeepSeek V3.1 (Reasoning) | 27.7 | 0.0 | $0.86 |
| DeepSeek R1 0528 (May '25) | 27.1 | 0.0 | $2.36 |
| DeepSeek V3 0324 | 22.3 | 0.0 | $1.25 |
| DeepSeek R1 (Jan '25) | 18.8 | 0.0 | $2.36 |
| DeepSeek R1 Distill Qwen 32B | 17.2 | 0.0 | Free |
| DeepSeek V3 (Dec '24) | 16.5 | 0.0 | $0.63 |
| DeepSeek R1 0528 Qwen3 8B | 16.4 | 0.0 | Free |
| DeepSeek R1 Distill Llama 70B | 16.0 | 47.0 | $0.88 |
| DeepSeek R1 Distill Qwen 14B | 15.8 | 0.0 | Free |
| DeepSeek-V2.5 (Dec '24) | 12.5 | 0.0 | Free |
| DeepSeek-V2.5 | 12.3 | 0.0 | Free |
| DeepSeek R1 Distill Llama 8B | 12.1 | 0.0 | Free |
| DeepSeek-Coder-V2 | 10.6 | 0.0 | Free |
| DeepSeek-V2-Chat | 9.1 | 0.0 | Free |
| DeepSeek R1 Distill Qwen 1.5B | 9.1 | 0.0 | Free |
| DeepSeek Coder V2 Lite Instruct | 8.5 | 0.0 | Free |
| DeepSeek LLM 67B Chat (V1) | 8.4 | 0.0 | Free |