Mercury 2 vs Mercury 2.5 Preview: which should you choose in 2026?
Mercury 2 (by Inception) and Mercury 2.5 Preview (by Inception) are compared below. Here is how they stack up on benchmarks, price, and capabilities, and which one to pick in 2026.
There are not enough shared, protocol-compatible benchmark results to declare a performance leader.
Mercury 2.5 Preview is about 5.6× cheaper on a blended 3:1 input/output basis ($0.0675 vs $0.375 per 1M tokens).
Mercury 2.5 Preview has the larger context window (260,000 tokens vs 128,000 tokens).
Choose Mercury 2 if…
- • your own prompt tests favor its output; shared comparable evidence does not identify a unique advantage
Choose Mercury 2.5 Preview if…
- • lower blended API cost matters for your workload
- • you work with longer documents, transcripts, or codebases
The benchmark count includes only results measured with a matching benchmark version and protocol. Arena scores are shown separately. Missing, preliminary, and incompatible data is not treated as a controlled win. Published point-score comparisons are labeled separately when protocol details are incomplete. For text-output models, the verdict also compares token pricing and context windows.
Performance benchmarks
Every value links to its source. A dash means that no reviewed result is available for that exact model and protocol.
| Benchmark | Mercury 2 | Mercury 2.5 Preview |
|---|---|---|
A 657-task benchmark of multi-step work across simulated SaaS applications in six business domains. The Artificial Analysis protocol reports a guardrail-aware score and is distinct from both the public Zapier split and the unrelated dynamic AutoBench framework. Guardrail-aware score | — | — |
A benchmark of difficult, verifiable information-seeking questions designed to measure an agent's ability to locate hard-to-find facts through web browsing. Accuracy | — | — |
A verified computer-use benchmark in which multimodal agents operate desktop applications and are graded from the resulting environment state. Mean task reward | — | — |
A human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests. Resolved | — | — |
Version 2.1 of the benchmark for completing realistic tasks in terminal environments. Harness, resource limits, and attempt count are part of the protocol. Mean task success | — | — |
A dynamic LLM evaluation framework in which models generate questions, answer them, and participate in reciprocal peer assessment. AutoBench is distinct from Zapier's AutomationBench. Weighted peer-assessment score | — | — |
The highest-quality subset of Graduate-Level Google-Proof Q&A, designed to test expert-level scientific reasoning in biology, physics, and chemistry. Accuracy | — | — |
A 2,500-question expert-level benchmark spanning dozens of academic fields. Tool-assisted and no-tools results are separate protocols and must not be merged. Accuracy | — | — |
| Arena preference scores | ||
Human preference score | 1347 ±11 | — |
Human preference score for code and web development | 1166 ±25 | — |
Benchmark sources
Reviewed evidence last updated 2026-08-09. Arena data last refreshed Sep 4, 2026.
Pricing, capabilities, and model facts
| Feature | Mercury 2 | Mercury 2.5 Preview |
|---|---|---|
| Context & model facts | ||
| Developer | Inception | Inception |
| API provider | Inception | Inception |
| Input context | 128,000 tokens | 260,000 tokens |
| Maximum output | 50,000 tokens | 65,536 tokens |
| Released | — | — |
| Added to Writingmate | Mar 4, 2026 | Aug 31, 2026 |
| License | Not available | Not available |
| Knowledge cutoff | — | — |
| Capabilities | ||
| Inputs | Text | Text |
| Outputs | Text | Text |
| Provider endpoint accepts tool parameters | Yes | Yes |
| Reasoning | Yes | Yes |
| Vision | No | No |
| Image Generation | No | No |
| Video Generation | No | No |
| API pricing | ||
| Input (per 1M tokens) | $0.25 | $0.04 |
| Output (per 1M tokens) | $0.75 | $0.15 |
| Blended 3:1 input/output | $0.375 | $0.0675 |
| API performance | ||
| p95 latency | Not measured | Not measured |
| Output throughput | Not measured | Not measured |
| Writingmate shows API performance only when both models have enough observations from the same measurement window, prompt profile, and provider. Third-party latency values are not copied into this table. | ||
Data sources
- Writingmate model catalog (pricing, limits, and availability)
Catalog data last updated Aug 31, 2026.
Mercury 2 vs Mercury 2.5 Preview FAQ
Which is better, Mercury 2 or Mercury 2.5 Preview?
There are not enough shared, protocol-compatible benchmark results to declare a performance leader. Mercury 2.5 Preview is about 5.6× cheaper on a blended 3:1 input/output basis ($0.0675 vs $0.375 per 1M tokens). Mercury 2.5 Preview has the larger context window (260,000 tokens vs 128,000 tokens).
Which model is cheaper to use through an API?
Mercury 2.5 Preview is about 5.6× cheaper on a blended 3:1 input/output basis ($0.0675 vs $0.375 per 1M tokens).
Which model supports more context?
Mercury 2.5 Preview has the larger context window (260,000 tokens vs 128,000 tokens).
Can I switch between Mercury 2 and Mercury 2.5 Preview?
Yes. Use the model selector on this page to open any current Writingmate model comparison. You can also run the same prompt with both models in Writingmate.
Related comparisons
More Mercury 2 comparisons
Qwen3.8 Max (0902)
Qwen
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.
Muse Spark 1.3 Contributor
Meta
Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows.
Muse Spark 1.3
Meta
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.
Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Granite 4.2 8B
IBM Granite
Granite 4.2 8B is a dense reasoning model from IBM.
Hy4 preview
Tencent
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.
More Mercury 2.5 Preview comparisons
Qwen3.8 Max (0902)
Qwen
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.
Muse Spark 1.3 Contributor
Meta
Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows.
Muse Spark 1.3
Meta
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.
Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Granite 4.2 8B
IBM Granite
Granite 4.2 8B is a dense reasoning model from IBM.
Hy4 preview
Tencent
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.