Skip to content
aiqbench

Inception-AI · model passport

Inception: Mercury 2

mercury-2
  • Cloud only
  • Proprietary licence
  • 128,000 context
  • Released 2026-10-13(first seen on LMArena)
8/27axes covered
Overall · LMArena
1,343#211 of 396
Best percentile
81.2IFBench (Artificial Analysis)
Cohort standing
41.4median 60.8

What the data says

Benchmarked on 8 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 4.3 pct — WebDev Arena (1,171)
  • 7.6 pct — Factuality Arena (1,368)

Uneven: 76.9 percentile points between its best and worst axis — 81.2 pct on IFBench (Artificial Analysis) versus 4.3 pct on WebDev Arena.

  • IFBench (Artificial Analysis)81.2 pct69.8%Verify →
  • Coding49.1 pct1,392Verify →
  • Hard prompts47.5 pct1,358Verify →
  • Overall47 pct1,343Verify →
  • Instruction following47 pct1,327Verify →
  • HHEM Hallucination (Vectara)21.9 pct87.7%Verify →
  • Factuality Arena7.6 pct1,368Verify →
  • WebDev Arena4.3 pct1,171Verify →
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Use it hosted

API model IDinception/mercury-2
Context length128,000 tokens
Max output50,000 tokens
Input price$0.25 per 1M tokens
Cached input price$0.03 per 1M tokens
Output price$0.75 per 1M tokens

API parameters this endpoint supports

Include reasoningMax tokensReasoningReasoning effortResponse formatStop sequencesStructured outputsTemperatureTool choiceTool calling

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"inception/mercury-2","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • mercury-2 stands at 41.4 (raw mean 38.2) — measured on 8 of 27 axes.

    standingtemplateVerify →

  • mercury-2 stands at 41.4 versus a cohort median of 60.8 across 168 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →