GPT-6.1 Sol vs Mercury 3: Specs & Benchmark Comparison

GPT-6.1 Sol is developed by OpenAI, while Mercury 3 comes from Inception. GPT-6.1 Sol was released in September 2026, and Mercury 3 followed a month later in October 2026.

We have 18 benchmark results for GPT-6.1 Sol and 12 benchmark results for Mercury 3, but they were measured on different benchmarks, so there is no like-for-like scoreboard.

Mercury 3 is the cheaper API at $0.10 per million input tokens and $0.35 per million output tokens, roughly 20 times cheaper than GPT-6.1 Sol at $2 and $10. Both accept a context window of about 1M tokens. GPT-6.1 Sol accepts text and images as input, while Mercury 3 accepts text.

CharacteristicGPT-6.1 SolMercury 3
CompanyOpenAIInception
Release DateSeptember 29, 2026October 19, 2026
Parameters——
MultimodalYesNo
Context (input)1.1M1.0M
Context (output)128K131K
Input Price / 1M$2.00$0.10
Output Price / 1M$10.00$0.35
Average Score60.5%60.1%

Verdict

Mercury 3 leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: GPT-6.1 Sol — 0.6, Mercury 3 — 0.6.

API Cost

Mercury 3 is 26.7x cheaper: input $0.10/1M vs $2.00/1M tokens.

Context Window

GPT-6.1 Sol supports a larger context: 1M vs 1M tokens.

Recency

Mercury 3 is newer: released 10/19/2026 vs 9/29/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — GPT-6.1 Sol or Mercury 3?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — GPT-6.1 Sol or Mercury 3?
Mercury 3 is cheaper for input: $0.10 per 1M tokens vs $2.00.
Which has a larger context window — GPT-6.1 Sol or Mercury 3?
GPT-6.1 Sol supports a larger context: 1,050,000 tokens vs 1,048,576.

The GPT-6.1 Sol and Mercury 3 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GPT-6.1 Sol or Mercury 3 page. See also the complete list of AI model comparisons.