Mercury Edit 2 vs Qwen3.5 397B-A17B vs Trinity Large Thinking
Too close to call on our weighted score (Qwen3.5 397B-A17B 56, Trinity Large Thinking 55, Mercury Edit 2 35). The right pick depends on what you value most.
InceptionMercury Edit 2
35/100- ECI—
- Price$0.25 / $0.75
- Context32K
Alibaba (Qwen)Qwen3.5 397B-A17B
56/100- ECI146.7
- Price$0.60 / $3.60
- Context262K
Arcee AITrinity Large Thinking
55/100- ECI—
- Price$0.25 / $0.80
- Context524K
Too close to call
It is close. Our weighted score puts them within 1 points (Qwen3.5 397B-A17B 56/100, Trinity Large Thinking 55/100, Mercury Edit 2 35/100), so choose by what matters most for your work: Mercury Edit 2 on price and Trinity Large Thinking for long inputs. 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 Edit 2Mercury Edit 2 $0.375 · Trinity Large Thinking $0.388 · Qwen3.5 397B-A17B $1.35 per 1M tokens (3:1 blend)
- Longest contextTrinity Large ThinkingTrinity Large Thinking 524,288 · Qwen3.5 397B-A17B 262,144 · Mercury Edit 2 32,000 tokens
- Widest inputsQwen3.5 397B-A17BMercury Edit 2: Text · Qwen3.5 397B-A17B: Text, Images, Audio, Video · Trinity Large Thinking: Text
- Self-hostingQwen3.5 397B-A17B and Trinity Large ThinkingPublishes downloadable weights (OpenMDW-1.1)
| Measure | Weight | Mercury Edit 2 | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|---|---|
| Price | 50% | 70 | 44 | 69 |
| Inputs & features | 30% | 0 | 90 | 35 |
| Context window | 20% | 0 | 37 | 49 |
| Overall | 100% | 35/100 | 56/100 | 55/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Mercury Edit 2Inception | Qwen3.5 397B-A17BAlibaba (Qwen) | Trinity Large ThinkingArcee AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 146.7 | — |
| ECI rank | — | #67 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 86.4% | — |
| FrontierMath Tiers 1–3Research-level mathematics | — | 31.2% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 88.9% | — |
| Price per million tokens | |||
| Input | $0.25 (best) | $0.60 | $0.25 (best) |
| Output | $0.75 (best) | $3.60 | $0.80 |
| Cached input | $0.025 (best) | — | $0.06 |
| Blended (3:1) | $0.375 (best) | $1.35 | $0.388 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Inception API | Official Alibaba API | Official Arcee API |
| Limits | |||
| Context window | 32,000 tokens | 262,144 tokens | 524,288 tokens (best) |
| Max output | 8,192 tokens | 65,536 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | No | Yes | Yes |
| Tool calling | No | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Proprietary | Open | OpenOpenMDW-1.1 |
| API model ID | mercury-edit-2 | qwen3.5-397b-a17b | trinity-large-thinking |
| API providers | 1 | 23 (best) | 6 |
| Released | Mar 30, 2026 | Feb 15, 2026 | Apr 1, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Mercury Edit 2$4.00
- Qwen3.5 397B-A17B$13.20
- Trinity Large Thinking$4.10
Which should you choose?
Which is better: Mercury Edit 2, Qwen3.5 397B-A17B or Trinity Large Thinking?
It is close. Our weighted score puts them within 1 points (Qwen3.5 397B-A17B 56/100, Trinity Large Thinking 55/100, Mercury Edit 2 35/100), so choose by what matters most for your work: Mercury Edit 2 on price and Trinity Large Thinking for long inputs. 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 Edit 2, Qwen3.5 397B-A17B or Trinity Large Thinking?
Mercury Edit 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 397B-A17B costs $0.60 input / $3.60 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.375 per million tokens for Mercury Edit 2 versus $0.388 for Trinity Large Thinking (1× as much) and $1.35 for Qwen3.5 397B-A17B (3.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Mercury Edit 2 has not been scored yet, Qwen3.5 397B-A17B has an ECI of 146.7 and Trinity Large Thinking has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Mercury Edit 2, Qwen3.5 397B-A17B and Trinity Large Thinking yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Mercury Edit 2 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 397B-A17B and 32,000 for Mercury Edit 2. Maximum output per response: Mercury Edit 2 up to 8,192, Qwen3.5 397B-A17B up to 65,536, Trinity Large Thinking up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Mercury Edit 2 accepts text; Qwen3.5 397B-A17B accepts text, images, audio and video; Trinity Large Thinking accepts text. Qwen3.5 397B-A17B handles the widest range of inputs.
Are any of these open source?
Qwen3.5 397B-A17B and Trinity Large Thinking publishes its weights (OpenMDW-1.1) and can be self-hosted; Mercury Edit 2 is proprietary.
Which is newer?
Trinity Large Thinking is the newest, released Apr 1, 2026. Mercury Edit 2 came out Mar 30, 2026; Qwen3.5 397B-A17B came out Feb 15, 2026.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.
