| Signal | Trinity Large Thinking | Delta | Mercury 2 |
|---|---|---|---|
Capabilities | 50 | -17 | |
Benchmarks | 63 | +3 | |
Pricing | 99 | 0 | |
Context window size | 77 | +4 | |
Recency | 100 | -- | |
Output Capacity | 82 | +3 | |
| Overall Result | 3 wins | of 6 | 2 wins |
Score History
62.7
current score
Trinity Large Thinking
right now
60.6
current score
arcee-ai
Inception
Mercury 2 saves you $2.50/month
That's $30.00/year compared to Trinity Large Thinking at your current usage level of 100K calls/month.
| Metric | Trinity Large Thinking | Mercury 2 | Winner |
|---|---|---|---|
| Overall Score | 63 | 61 | Trinity Large Thinking |
| Rank | #135 | #137 | Trinity Large Thinking |
| Quality Rank | #135 | #137 | Trinity Large Thinking |
| Adoption Rank | #135 | #137 | Trinity Large Thinking |
| Parameters | -- | -- | -- |
| Context Window | 262K | 128K | Trinity Large Thinking |
| Pricing | $0.25/$0.80/M | $0.25/$0.75/M | -- |
| Signal Scores | |||
| Capabilities | 50 | 67 | Mercury 2 |
| Benchmarks | 63 | 60 | Trinity Large Thinking |
| Pricing | 99 | 99 | Mercury 2 |
| Context window size | 77 | 73 | Trinity Large Thinking |
| Recency | 100 | 100 | Trinity Large Thinking |
| Output Capacity | 82 | 78 | Trinity Large Thinking |
Our score (0-100) is driven by benchmark performance (90%) from Arena Elo ratings, MMLU, GPQA, HumanEval, SWE-bench, and 15+ standardized evaluations. Capabilities and context window serve as tiebreakers (10%). Learn more about our methodology.
Scores 63/100 (rank #135), placing it in the top 54% of all 290 models tracked.
Scores 61/100 (rank #137), placing it in the top 53% of all 290 models tracked.
With only a 2-point gap, these models are in the same performance tier. The practical difference in output quality is minimal - your choice should depend on pricing, latency requirements, and specific feature needs.
Mercury 2 offers 5% better value per quality point. At 1M tokens/day, you'd spend $15.00/month with Mercury 2 vs $15.75/month with Trinity Large Thinking - a $0.75 monthly difference.
Both models have comparable response speeds. For most applications, the latency difference is negligible.
When latency matters most: Interactive chatbots, IDE code completion, real-time translation, and user-facing applications where response time directly impacts experience. For batch processing, background summarization, or offline analysis, latency is less critical.
Code generation & review
Based on overall model capabilities and architecture for coding tasks like generating functions, debugging, and refactoring
Customer support chatbot
Suitable for user-facing chat with competitive response times. Mercury 2 also offers lower per-token costs for high-volume support
Long document analysis
Larger context window (262K tokens) can process longer documents, contracts, and research papers in a single pass
Batch data extraction
Lower output pricing ($0.75/M) reduces costs when processing thousands of records daily
Creative writing & content
Higher overall composite score (63/100) correlates with better nuance, coherence, and style in long-form content
Trinity Large Thinking and Mercury 2 are extremely close in overall performance (only 2.1000000000000014 points apart). Your best choice depends entirely on which specific strengths matter most for your use case.
Best for Quality
Trinity Large Thinking
Marginally better benchmark scores; both are excellent
Best for Cost
Mercury 2
5% lower pricing; better value at scale
Best for Reliability
Trinity Large Thinking
Higher uptime and faster response speeds
Best for Prototyping
Trinity Large Thinking
Stronger community support and better developer experience
Best for Production
Trinity Large Thinking
Wider enterprise adoption and proven at scale
by arcee-ai
| Capability | Trinity Large Thinking | Mercury 2 |
|---|---|---|
| Vision (Image Input) | ||
| Function Calling | ||
| Streaming | ||
| JSON Modediffers | ||
| Reasoning | ||
| Web Search | ||
| Image Output |
arcee-ai
Inception
Mercury 2 saves you $0.0600/month
That's 4% cheaper than Trinity Large Thinking at 1,000 tokens/request and 100 requests/day.
Assumes 60% input / 40% output token ratio per request. Actual costs may vary based on your usage pattern.
| Parameter | Trinity Large Thinking | Mercury 2 |
|---|---|---|
| Context Window | 262K | 128K |
| Max Output Tokens | 80,000 | 50,000 |
| Open Source | Yes | No |
| Created | Apr 1, 2026 | Mar 4, 2026 |