Cost-efficiency ranking
How many intelligence points one dollar buys. Higher is better, but remember that models differ in output-token efficiency.
| # | Model | Value | Vs. leader | Composite v5 | Output $ | Type |
|---|---|---|---|---|---|---|
| 1 | Claude Haiku 5.5Anthropic | 180.0 | #1 | 36.0 | $0.50 | |
| 2 | MiniMax M3.1 FlashMiniMax | 110.7 | 62% | 29.0 | $0.60 | |
| 3 | DeepSeek V4.1 Flash Open weightsDeepSeek | 62.9 | 35% | 33.0 | $1.20 | Open weights |
| 4 | MiMo-V2.6 Pro Open weightsXiaomi | 49.0 | 27% | 30.0 | $1.40 | Open weights |
| 5 | GPT-6.1 TerraOpenAI | 25.6 | 14% | 51.3 | $5.00 | |
| 6 | Mistral Large 4 Open weightsMistral | 24.8 | 14% | 26.0 | $2.10 | Open weights |
| 7 | GLM-5.3 Open weightsZ.ai | 14.9 | 8% | 32.0 | $4.40 | Open weights |
| 8 | GPT-6.1 SolOpenAI | 13.7 | 8% | 54.6 | $10.00 | |
| 9 | Claude Sonnet 5.5Anthropic | 13.6 | 8% | 54.5 | $10.00 | |
| 10 | Gemini 4 ArgonGoogle | 12.6 | 7% | 50.4 | $10.00 | |
| 11 | DeepSeek V4 Pro Open weightsDeepSeek | 11.6 | 6% | 23.0 | $3.96 | Open weights |
| 12 | Kimi K3.1 Pro Open weightsMoonshot AI | 11.5 | 6% | 46.0 | $10.00 | Open weights |
| 13 | Grok 4.7xAI | 11.4 | 6% | 34.3 | $6.00 | |
| 14 | Qwen3.8 MaxAlibaba Qwen | 11.3 | 6% | 34.0 | $6.00 | |
| 15 | Gemini 4 CarbonGoogle | 7.5 | 4% | 60.0 | $20.00 | |
| 16 | Claude Opus 5.5Anthropic | 7.4 | 4% | 59.1 | $20.00 | |
| 17 | Muse WonderMeta | 5.5 | 3% | 44.0 | $20.00 | |
| 18 | GPT-6 AstraOpenAI | 2.8 | 2% | 56.9 | $50.00 | |
| 19 | Claude Fable 5.1Anthropic | 2.5 | 1% | 49.0 | $50.00 |