mercury-2.5-preview
mercury-2.5-preview is capable in long context and behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, math, multimodal tasks, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Agentic, Safety, Math, Multimodal, Multilingual or Instruction Following.
Price
$0.25input$0.75outputper million tokens
From Artificial Analysis · 2 providers tracked · All prices
Evidence
10results on10benchmarks
- 10 aggregator
From 1 source · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputsReasoning
As listed by OpenRouter
mercury-2.5-preview benchmark results
10 results on 10 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
23.6% behind the leader1 of 3 ranked benchmarks measured
- 71.67Oct 8, 2026
34.2% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy22.65Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination19.67Oct 8, 2026omniscienceNonHallucination
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- Humanity's Last Exam11.77Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- SciCode38.54Oct 8, 2026aa_scicode
0 of 7 ranked benchmarks measured
- 0.00Oct 8, 2026
- Terminal-Bench 4.00.00Oct 8, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence12.34Oct 8, 2026aa_intelligence_index
- -39.48Oct 8, 2026
mercury-2.5-preview: common questions
Who makes mercury-2.5-preview?
mercury-2.5-preview is made by Inception.
When was mercury-2.5-preview released?
mercury-2.5-preview was released on Sep 8, 2026, according to Artificial Analysis.
What is mercury-2.5-preview good at?
mercury-2.5-preview is capable in long context and behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, math, multimodal tasks, multilingual tasks, or instruction following.
How much does mercury-2.5-preview cost?
mercury-2.5-preview costs $0.25 per million input tokens and $0.75 per million output tokens, according to Artificial Analysis. We track its price at 2 providers. At a mix of three input tokens to one output token, it is cheaper than 66% of the 330 priced models we track.
How many benchmarks has mercury-2.5-preview been tested on?
We track 10 results for mercury-2.5-preview on 10 benchmarks from 1 source. The latest was recorded on Oct 8, 2026.
Which API features does mercury-2.5-preview support?
OpenRouter lists tool calling, structured outputs, and reasoning for mercury-2.5-preview.
About this record
Where mercury-2.5-preview's numbers come from, and every name it appears under.
- Tracked since
- Sep 2, 2026
- Newest source mention
- Sep 24, 2026
Where the results come from
Verification: 10 scores · 0 independently verified · 10 aggregator-attributed. How these tiers are assigned
From 1 source on 1 site. Artificial Analysis supplies all of them. Bars are coloured by trust tier.
- artificialanalysis.ai10