Deterministic empirical evaluation of 24 frontier AI models and SWE agents across 6 verified task vectors, real token unit economics, and meta-evaluator credibility audits.
| System & Version | Vendor | Model Type | Pricing | Cost / 1k | Evidence |
|---|---|---|---|---|---|
| Claude 4 Opus v4.1 | Anthropic | Proprietary | subscription | £0.0062 | [Verified N≥5] |
| GPT-6 Omni v6.2-prod | OpenAI | Proprietary | subscription | £0.0052 | [Verified N≥5] |
| Gemini 3 Pro v3.1-preview | Google DeepMind | Proprietary | payg | £0.0026 | [Verified N≥5] |
| Grok 3 Agent v3.0-live | xAI | Proprietary | subscription | £0.0041 | [Verified N≥5] |
| Llama 4 405B Instruct v4.0 | Meta Open Source | Open Weights | free | £0.0011 | [Verified N≥5] |
| Claude 3.7 Sonnet Hybrid v3.7 | Anthropic | Proprietary | subscription | £0.0048 | [Verified N≥5] |
| GPT-5 Turbo v5.1 | OpenAI | Proprietary | payg | £0.0031 | [Verified N≥5] |
| Gemini 2.5 Flash v2.5 | Google DeepMind | Proprietary | payg | £0.0007 | [Verified N≥5] |
| DeepSeek V3 MoE v3.0 | DeepSeek AI | Open Weights | payg | £0.0005 | [Verified N≥5] |
| Qwen 2.5 Max v2.5 | Alibaba Cloud | Proprietary | payg | £0.0018 | [Verified N≥5] |
| Mistral Large 3 v3.0 | Mistral AI | Proprietary | payg | £0.0035 | [Verified N≥5] |
| Command R+ 2 v2.0 | Cohere | Proprietary | subscription | £0.0055 | [Verified N≥5] |
| Llama 4 70B v4.0 | Meta Open Source | Open Weights | free | £0.0004 | [Verified N≥5] |
| Devin 2.0 SWE Agent v2.2 | Cognition AI | Proprietary | subscription | £0.0820 | [Verified N≥5] |
| Cursor Composer v3 v3.0 | Anysphere | Proprietary | subscription | £0.0125 | [Verified N≥5] |