BenchLM recommendation
Best Value Multimodal AI Model in 2026 — Cost-Adjusted Rankings
As of August 18, 2026, the top model in best value multimodal ai model on the BenchLM leaderboard is GPT-5.6 Luna with a score of 55.1.
Last verified: August 18, 2026
Multimodal workloads — processing images, charts, documents, and screenshots — often involve large inputs that drive up token costs quickly. This ranking divides each model's weighted multimodal score (MMMU-Pro, OfficeQA-Pro) by output token price. For document processing pipelines and visual AI applications running at scale, the value leaders here offer the best multimodal reasoning per dollar spent.
Unless noted otherwise, ranking surfaces on this page use BenchLM's provisional leaderboard lane rather than the stricter sourced-only verified leaderboard.
Bottom line: Multimodal inputs are large and expensive. Gemini 3.1 Flash-Lite dominates value with strong multimodal scores at the lowest price point.
GPT-5.6 Luna leads this ranking with a score of 55.08, followed by MiniMax M3 (39.67) and Inkling-Small (35.56). There is a significant gap between the leading models and the rest of the field.
The best open-weight option is MiniMax M3 (ranked #2 with a score of 39.67). Open-weight models are highly competitive in this category — self-hosting is a viable alternative to proprietary APIs.
This ranking uses provisional weighted averages across the scoring benchmarks in multimodalGrounded. For detailed model profiles, click any model name below. To compare two specific models head-to-head, use the "vs #" links.
What changed
Gemini 3.1 Flash-Lite leads multimodal value — best visual reasoning per dollar.
GPT-4.1 nano strong multimodal value in OpenAI's lineup.
Gemini 2.5 Flash good multimodal value with broader capabilities.
How to choose
Full Rankings (23 models)
Key Takeaways
The best value model is GPT-5.6 Luna by OpenAI with a provisional Score/$ ratio of 55.08 (score: 66.1, output: $1.2/1M tokens).
The best open-weight model is MiniMax M3 at position #2.
23 models are included in this ranking.
Score in Context
What these scores mean
Value scores divide the weighted multimodal score by output token price (per 1M tokens). Higher means more capability per dollar. Models with no listed price are excluded.
Known limitations
Value rankings favor cheap models even if absolute performance is modest. A model scoring half as well at one-tenth the price wins on value — but may not meet your quality bar. Always check raw scores alongside value rankings.
Explore More
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.