Best Value Agentic AI Model in 2026 — Cost-Adjusted Rankings
As of November 16, 2026, the top model among value agentic AI model on the BenchLM leaderboard is Ministral 3 3B with a score of 312.5.
Bottom line: Agentic tasks are token-intensive — value matters more here than almost anywhere.
Full Rankings (91 ranked)
Key Takeaways
The best value model is Ministral 3 3B by Mistral with a provisional Score/$ ratio of 312.5 (score: 31.3, output: $0.1/1M tokens).
The best open-weight model is Ministral 3 3B at position #1.
91 models are included in this ranking.
Score in Context
What these scores mean
Value scores divide the weighted agentic 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.
About this ranking
Ranking data as of November 16, 2026
Agentic workloads are token-intensive — agents loop, retry, and chain multiple calls. That makes cost-per-token a critical factor alongside raw capability. This ranking divides each model's weighted agentic score (Terminal-Bench 2.0, BrowseComp, OSWorld-Verified) by its output token price. The result shows which models give you the most agent capability per dollar. If you're building production AI agents with budget constraints, this is where you start.
Unless noted otherwise, ranking surfaces on this page use BenchLM’s provisional leaderboard lane rather than the stricter sourced-only verified leaderboard.
Ministral 3 3B leads this ranking with a score of 312.5, followed by MiMo-V2.6-Flash (221.32) and Ministral 3 8B (208). There is a significant gap between the leading models and the rest of the field.
The best open-weight option is Ministral 3 3B (ranked #1 with a score of 312.5). 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 agentic. For detailed model profiles, click any model name above. To compare two specific models head-to-head, use the "vs #" links.
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 7,000+ subscribers.
One email each week. Unsubscribe anytime.