ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Mercury 2 vs Trinity Large Thinking vs Qwen3.5 9B Base

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Inception

    Mercury 2

    Released Feb 24, 2026

    53/100
    • ECI—
    • Price$0.25 / $0.75
    • Context128K
  2. Arcee AI

    Trinity Large Thinking

    Released Apr 1, 2026Beta

    55/100
    • ECI—
    • Price$0.25 / $0.80
    • Context524K
  3. Alibaba (Qwen)

    Qwen3.5 9B Base

    Released Feb 26, 2026

    51/100
    • ECI—
    • Price$0.30 / $0.807
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Trinity Large Thinking 55/100, Mercury 2 53/100, Qwen3.5 9B Base 51/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceMercury 2Mercury 2 $0.375 · Trinity Large Thinking $0.388 · Qwen3.5 9B Base $0.427 per 1M tokens (3:1 blend)
  • Longest contextTrinity Large ThinkingTrinity Large Thinking 524,288 · Qwen3.5 9B Base 262,144 · Mercury 2 128,000 tokens
  • Widest inputsQwen3.5 9B BaseMercury 2: Text · Trinity Large Thinking: Text · Qwen3.5 9B Base: Text, Images, Video
  • Self-hostingTrinity Large Thinking and Qwen3.5 9B BasePublishes downloadable weights (OpenMDW-1.1 and Apache-2.0)
How the score is built
MeasureWeightMercury 2Trinity Large ThinkingQwen3.5 9B Base
Price50%676665
Inputs & features30%453535
Context window20%325443
Specs & price only100%53/10055/10051/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Mercury 2 vs Trinity Large Thinking vs Qwen3.5 9B Base specifications side by side
SpecificationMercury 2InceptionTrinity Large ThinkingArcee AIQwen3.5 9B BaseAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.25 (best)$0.25 (best)$0.30
Output$0.75 (best)$0.80$0.807
Cached input$0.025 (best)$0.06—
Blended (3:1)$0.375 (best)$0.388$0.427
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Inception APIOfficial Arcee APIMedian of 1 providers
Limits
Context window128,000 tokens524,288 tokens (best)262,144 tokens
Max output50,000 tokens262,144 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYeslow · medium · highYesNo
Tool callingYesYesNo
Structured outputYesNoNo
Availability
WeightsProprietaryOpenOpenMDW-1.1OpenApache-2.0
API model IDmercury-2trinity-large-thinking—
API providers2 (best)2 (best)1
ReleasedFeb 24, 2026Apr 1, 2026Feb 26, 2026
Knowledge cutoff———
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Mercury 2$4.00
  • Trinity Large Thinking$4.10
  • Qwen3.5 9B Base$4.61
04 — Questions

Which should you choose?

Which is better: Mercury 2, Trinity Large Thinking or Qwen3.5 9B Base?

There is not enough shared capability evidence to name an overall winner. The scores (Trinity Large Thinking 55/100, Mercury 2 53/100, Qwen3.5 9B Base 51/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Mercury 2, Trinity Large Thinking or Qwen3.5 9B Base?

Mercury 2 is cheaper at $0.25 input / $0.75 output per million tokens (official Inception API price). Trinity Large Thinking costs $0.25 input / $0.80 output per million tokens (official Arcee API price); Qwen3.5 9B Base costs $0.30 input / $0.807 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.375 per million tokens for Mercury 2 versus $0.388 for Trinity Large Thinking (1× as much) and $0.427 for Qwen3.5 9B Base (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Mercury 2 has not been scored yet, Trinity Large Thinking has not been scored yet and Qwen3.5 9B Base has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Mercury 2, Trinity Large Thinking and Qwen3.5 9B Base yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen3.5 9B Base does not support tool calling, which most coding agents need.

Which has the bigger context window?

Trinity Large Thinking has the largest context window at 524,288 tokens, against 262,144 for Qwen3.5 9B Base and 128,000 for Mercury 2. Maximum output per response: Mercury 2 up to 50,000, Trinity Large Thinking up to 262,144, Qwen3.5 9B Base up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Mercury 2 accepts text; Trinity Large Thinking accepts text; Qwen3.5 9B Base accepts text, images and video. Qwen3.5 9B Base handles the widest range of inputs.

Are any of these open source?

Trinity Large Thinking and Qwen3.5 9B Base publishes its weights (OpenMDW-1.1 and Apache-2.0) and can be self-hosted; Mercury 2 is proprietary.

Which is newer?

Trinity Large Thinking is the newest, released Apr 1, 2026. Qwen3.5 9B Base came out Feb 26, 2026; Mercury 2 came out Feb 24, 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.