// ranked · November 2026
Best Value LLM
Ranked by measured cost per point of LiveBench overall score: the dollars LiveBench actually spent running the model, divided by the score it earned. It captures verbosity and reasoning-token spend that list prices hide.
GPT-6 Luna delivers LiveBench capability most cheaply, at $0.0012 of measured spend per overall point (score 64.6). MiniMax M3.1 Flash is next at $0.0015.
GPT-6 Luna vs MiniMax M3.1 Flash, head to headTop 10
| # | Model | $ per point | Blended / 1M | Context | LiveBench | Capabilities |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Luna openai/gpt-6-luna | $0.0012 | $0.200 | 1.1M | 64.6 | reasoningtoolsvision |
| 2 | MiniMax M3.1 Flash minimax/minimax-m3.1-flash | $0.0015 | $0.131 | 1.0M | 66.9 | reasoningtoolsvision |
| 3 | GLM 5.3 Flash z-ai/glm-5.3-flash | $0.0016 | $0.237 | 1.0M | 62.1 | reasoningtoolsvision |
| 4 | Gemma 4 31B google/gemma-4-31b-it | $0.0017 | $0.250 | 262K | 38.7 | reasoningtoolsvision |
| 5 | MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0018 | $0.544 | 1.1M | 68.5 | reasoningtoolsvision |
| 6 | DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0018 | $0.262 | 1.0M | 72.9 | reasoningtoolsvision |
| 7 | Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.0030 | $0.237 | 1.0M | 50.2 | reasoningtoolsvision |
| 8 | GPT-6.1 Terra openai/gpt-6.1-terra | $0.0067 | $2.00 | 1.1M | 77.8 | reasoningtoolsvision |
| 9 | GPT-6.1 Sol openai/gpt-6.1-sol | $0.0082 | $4.00 | 1.1M | 84.1 | reasoningtoolsvision |
| 10 | Qwen3.8 27B qwen/qwen3.8-27b | $0.0084 | $0.581 | 1.0M | 58.4 | reasoningtoolsvision |
18 more models qualify — see the full leaderboard.
FAQ
Which LLM gives the best value for money in November 2026?
GPT-6 Luna delivers LiveBench capability most cheaply, at $0.0012 of measured spend per overall point (score 64.6). MiniMax M3.1 Flash is next at $0.0015.
How is this ranking produced?
Ranked by measured cost per point of LiveBench overall score: the dollars LiveBench actually spent running the model, divided by the score it earned. It captures verbosity and reasoning-token spend that list prices hide.
Other rankings
How this ranking is produced
- One metric, stated above — nothing here is weighted or scored by us. Scores come from LiveBench release 2026-10-25; models without a published run don't appear in score-based rankings.
- Price, context and capabilities — live from OpenRouter, refreshed every 15 minutes.
- Ties — scores less than a point apart are called a tie; effort settings alone move a LiveBench score by more than that.
A public benchmark is someone else's workload. Before committing, see LLM & agent evaluation.