| Signal | GPT-4o-mini Search Preview | Delta | Mercury 2 |
|---|---|---|---|
Capabilities | 50 | -17 | |
Benchmarks | 74 | +15 | |
Pricing | 99 | +0 | |
Context window size | 81 | -- | |
Recency | 61 | -39 | |
Output Capacity | 70 | -8 | |
| Overall Result | 2 wins | of 6 | 3 wins |
Score History
60.8
current score
Mercury 2
right now
61
current score
OpenAI
Inception
GPT-4o-mini Search Preview saves you $17.50/month
That's $210.00/year compared to Mercury 2 at your current usage level of 100K calls/month.
| Metric | GPT-4o-mini Search Preview | Mercury 2 | Winner |
|---|---|---|---|
| Overall Score | 61 | 61 | Mercury 2 |
| Rank | #134 | #133 | Mercury 2 |
| Quality Rank | #134 | #133 | Mercury 2 |
| Adoption Rank | #134 | #133 | Mercury 2 |
| Parameters | -- | -- | -- |
| Context Window | 128K | 128K | -- |
| Pricing | $0.15/$0.60/M | $0.25/$0.75/M | -- |
| Signal Scores | |||
| Capabilities | 50 | 67 | Mercury 2 |
| Benchmarks | 74 | 60 | GPT-4o-mini Search Preview |
| Pricing | 99 | 99 | GPT-4o-mini Search Preview |
| Context window size | 81 | 81 | GPT-4o-mini Search Preview |
| Recency | 61 | 100 | Mercury 2 |
| Output Capacity | 70 | 78 | Mercury 2 |
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 61/100 (rank #134), placing it in the top 54% of all 290 models tracked.
Scores 61/100 (rank #133), placing it in the top 54% of all 290 models tracked.
With only a 0-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.
GPT-4o-mini Search Preview offers 25% better value per quality point. At 1M tokens/day, you'd spend $11.25/month with GPT-4o-mini Search Preview vs $15.00/month with Mercury 2 - a $3.75 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
Higher benchmark score (0/100) indicates stronger performance on coding tasks like generating functions, debugging, and refactoring
Customer support chatbot
Faster response time (speed score 0/100) is critical for user-facing chat. GPT-4o-mini Search Preview also offers lower per-token costs for high-volume support
Long document analysis
Larger context window (128K tokens) can process longer documents, contracts, and research papers in a single pass
Batch data extraction
Lower output pricing ($0.60/M) reduces costs when processing thousands of records daily
Creative writing & content
Higher overall composite score (61/100) correlates with better nuance, coherence, and style in long-form content
GPT-4o-mini Search Preview and Mercury 2 are extremely close in overall performance (only 0.20000000000000284 points apart). Your best choice depends entirely on which specific strengths matter most for your use case.
Best for Quality
GPT-4o-mini Search Preview
Marginally better benchmark scores; both are excellent
Best for Cost
GPT-4o-mini Search Preview
25% lower pricing; better value at scale
Best for Reliability
GPT-4o-mini Search Preview
Higher uptime and faster response speeds
Best for Prototyping
GPT-4o-mini Search Preview
Stronger community support and better developer experience
Best for Production
GPT-4o-mini Search Preview
Wider enterprise adoption and proven at scale
by OpenAI
| Capability | GPT-4o-mini Search Preview | Mercury 2 |
|---|---|---|
| Vision (Image Input) | ||
| Function Callingdiffers | ||
| Streaming | ||
| JSON Mode | ||
| Reasoningdiffers | ||
| Web Searchdiffers | ||
| Image Output |
OpenAI
Inception
GPT-4o-mini Search Preview saves you $0.3600/month
That's 27% cheaper than Mercury 2 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 | GPT-4o-mini Search Preview | Mercury 2 |
|---|---|---|
| Context Window | 128K | 128K |
| Max Output Tokens | 16,384 | 50,000 |
| Open Source | No | No |
| Created | Mar 12, 2025 | Mar 4, 2026 |