Mercury 2

Inception · released 2026-02-20 · 1 offers

Output 509 tokens/sFirst token 5.9 sContext 128K tokens

Top 1 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

#	Provider	Platform	Raw input $/1M	Raw output $/1M	Adjusted $/task
1	Inception	OpenRouter	$0.250	$0.750

2 of 7 inputs6 radar axes: DesignArena's two boards share one

26.6

includes −2.3 for its Benchmaxxing signal (from 28.9; why, switch off in Options)

AA Coding 31.1Coding Agent v1.4 —AA Intelligence 11.5AA Agentic 4.0Epoch ECI —Software ECI —DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

17 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

AA-Briefcase14280 Elo2026-09-10
AA-Briefcase published 2026-09-10 ↗ · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.
GDPval-AA v230646 Elo2026-09-10
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench Hard (AA)6826.5%2026-09-10
Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.
Terminal-Bench v2.1 (AA)3227.3%2026-09-10
Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.
Terminal-Bench v4.0 (AA)180.0%2026-09-10
Terminal-Bench v4.0 (AA) v4.0 ↗ · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.
AA Agentic Index304.002026-09-18
AA Agentic Index published 2026-09-18 ↗ · Published board — Artificial Analysis publishes one Agentic Index per model, measured on its primary configuration and relayed by OpenRouter's Benchmarks API; the value is attached at family scope on the deterministic representative. Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

SciCode (AA subproblems) v1.0.12037.7%2026-09-10
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index3731.12026-09-19
AA Coding Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

IFBench (AA single-turn)8469.8%2026-09-10
IFBench (AA single-turn) published 2026-09-10 ↗ · Published board — Tests precise single-turn instructions with deterministic rule checks.

Humanity's Last Exam (AA text-only)6817.1%2026-09-10
Humanity's Last Exam (AA text-only) published 2026-09-10 ↗ · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index33-50.72026-09-10
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.

GDP.pdf (AA)263.8%2026-09-10
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.14243.7%2026-09-10
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

AA Intelligence Index5011.52026-09-19
AA Intelligence Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

CritPt (AA)600.8%2026-09-10
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)6177.0%2026-09-10
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.

AutomationBench-AA v1.0.6221.7%2026-09-10
AutomationBench-AA v1.0.6 ↗ · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
τ²-Bench Telecom (AA)6370.8%2026-09-10
τ²-Bench Telecom (AA) published 2026-09-10 ↗ · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.
τ³-Banking (AA) v1.0.1289.5%2026-09-10
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.

Missing coverage · 126 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Token offers by platform · 1 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

1 offers within the active global filters; “—” means the catalog is active but no public token price is available.

Inception