Mercury 2.5 vs MiniMax M3: which should you choose in 2026?
Mercury 2.5 (by Inception) and MiniMax M3 (by MiniMax) 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 is about 7.8× cheaper on a blended 3:1 input/output basis ($0.0675 vs $0.525 per 1M tokens).
MiniMax M3 has the larger context window (1,048,576 tokens vs 260,000 tokens).
Choose Mercury 2.5 if…
- • lower blended API cost matters for your workload
Choose MiniMax M3 if…
- • you work with longer documents, transcripts, or codebases
- • you need image inputs
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 2.5 | MiniMax M3 |
|---|---|---|
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 | — | 75.2% OSWorld |
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 | — | 92.9% Artificial Analysis |
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 | — | 39.0% Artificial Analysis |
A contamination-resistant benchmark refreshed on a fixed release cadence. Scores from different LiveBench releases must never be compared as the same protocol. Mean of category averages | — | 67.3% LiveBench |
| Arena preference scores | ||
Human preference score | — | 1443 ±4 |
Human preference score for code and web development | — | 1486 ±7 |
Benchmark sources
- Arena AI leaderboard
- OSWorld-Verified Results
- GPQA Diamond Benchmark Leaderboard
- Humanity's Last Exam Benchmark Leaderboard
- LiveBench 2026-06-25 Leaderboard
Reviewed evidence last updated 2026-08-09. Arena data last refreshed Sep 9, 2026.
Pricing, capabilities, and model facts
| Feature | Mercury 2.5 | MiniMax M3 |
|---|---|---|
| Context & model facts | ||
| Developer | Inception | MiniMax |
| API provider | Inception | MiniMax |
| Input context | 260,000 tokens | 1,048,576 tokens |
| Maximum output | 65,536 tokens | 512,000 tokens |
| Released | — | — |
| Added to Writingmate | Sep 8, 2026 | May 31, 2026 |
| License | Not available | Not available |
| Knowledge cutoff | — | — |
| Capabilities | ||
| Inputs | Text | Text, Image, Video |
| Outputs | Text | Text |
| Provider endpoint accepts tool parameters | Yes | Yes |
| Reasoning | Yes | Yes |
| Vision | No | Yes |
| Image Generation | No | No |
| Video Generation | No | No |
| API pricing | ||
| Input (per 1M tokens) | $0.04 | $0.30 |
| Output (per 1M tokens) | $0.15 | $1.20 |
| Blended 3:1 input/output | $0.0675 | $0.525 |
| 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 Sep 8, 2026.
Why Pay for Multiple Subscriptions?
Comparing Mercury 2.5 from Inception with MiniMax M3 from MiniMax? Instead of managing separate API keys and subscriptions, get both with Writingmate.
| Plan | Price | Mercury 2.5 | MiniMax M3 | AI Images | AI Video |
|---|---|---|---|---|---|
Writingmate Pro Most popular | $20/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | Sora 2, VEO 3.1 |
Writingmate Ultimate Power users | $60/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | Sora 2, VEO 3.1 |
Mercury 2.5 vs MiniMax M3 FAQ
Which is better, Mercury 2.5 or MiniMax M3?
There are not enough shared, protocol-compatible benchmark results to declare a performance leader. Mercury 2.5 is about 7.8× cheaper on a blended 3:1 input/output basis ($0.0675 vs $0.525 per 1M tokens). MiniMax M3 has the larger context window (1,048,576 tokens vs 260,000 tokens).
Which model is cheaper to use through an API?
Mercury 2.5 is about 7.8× cheaper on a blended 3:1 input/output basis ($0.0675 vs $0.525 per 1M tokens).
Which model supports more context?
MiniMax M3 has the larger context window (1,048,576 tokens vs 260,000 tokens).
Can I switch between Mercury 2.5 and MiniMax M3?
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 2.5 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 MiniMax M3 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.
Qwen3.8 Flash
Qwen
Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
GLM 5.3 Flash
Z.AI
GLM-5.3-Flash is a native multimodal model from Z.ai.