A model benchmark shows Muse Spark far ahead of Grok-4.20 on score vs cost
cis_female · x · 2026-07-21
The attached comparison table ranks several models by score and first-call cost.
Top of the table is Claude Fable 5 at 4.30, followed by Claude Opus 4.8 at 4.06. Meta’s Muse Spark 1.1 scores 3.88 at a much lower listed cost, while GLM-5.2, GPT-5.6 variants, Gemini 3.1 Pro, DeepSeek V4 Pro, Qwen 3.7 Plus, Grok-4.20, and MiniMax M3 trail behind.
The poster’s point is that the cheap-new-model narrative does not hold uniformly: some low-cost models perform very well, but others do not.
Related event: Testing LLMs on Relationship Understanding with 600k Tokens(6 posts)→
More from Models
- Leaked Terminal-Bench 4.0 chart shows GPT-6.1 Terra leading at lowest cost, unverified — Angaisb_ · 2026-10-27
- GPT-6.1 Terra rolls out to all Plus, Pro, Enterprise and Edu users — OpenAI · 2026-10-27
- OpenAI launches GPT-6.1 Terra with 50% lower API prices than GPT-5.6 Terra — OpenAI · 2026-10-27
- In cyber, intention matters little: Chintala on model info leaks, and what users should do — brhydon · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27
- Ortet's first health eval: 34 open-weight models, 50 tasks, generic rankings fall short — thegautamkamath · 2026-10-27