Inception, proprietary
Mercury 2
Mercury 2 by Inception ranks 175th of 354 ranked models on the Noometry Index as of October 2026, with a score of 39.1. Its strongest category is long context, where it ranks 154th. API pricing starts at $0.25 per million input tokens and $0.75 per million output tokens, with a 128K-token context window.
Last verified
Specifications
- Noometry rank
- #175 of 354
- Index score
- 39.1
- Evidence
- Confirmed 17 results
- Provider
- Inception
- Released
- February 20, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 128K
- Max output
- 50K
- Input price
- $0.25 / M
- Output price
- $0.75 / M
- Blended price
- $0.38 / M
- Output speed
- Not measured
- Value
- #56 of 219
- Knowledge cutoff
- January 2025
- Input
- text
Category scores
Each category score combines every public result we have in that category.
- Coding 33.5
- Reasoning 23.8
- Knowledge 36.2
- Multilingual 46.6
- Instruction Following 70.2
- Long Context 40.5
- Writing & Preference 53.8
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 33.5 | #255 | 4 |
| Reasoning | 23.8 | #170 | 2 |
| Knowledge | 36.2 | #172 | 2 |
| Multilingual | 46.6 | #157 | 1 |
| Instruction Following | 70.2 | #165 | 1 |
| Long Context | 40.5 | #154 | 1 |
| Writing & Preference | 53.8 | #155 | 3 |
Strengths and weaknesses
Categories where Mercury 2 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 23.8 | +0.2 | #170 of 350, top 49% |
| Writing & Preference | 53.8 | +0.0 | #155 of 312, top 50% |
| Long Context | 40.5 | −0.5 | #154 of 296, top 53% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 33.5 | −5.2 | #255 of 340, top 75% |
| Knowledge | 36.2 | −1.1 | #172 of 314, top 55% |
| Instruction Following | 70.2 | −1.1 | #165 of 305, top 55% |
Closest competitors
The models ranked just above and below Mercury 2. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Step 2 16k Exp 202412 | #171 | 39.2 | — | — | Compare |
| Qwen3 32B | #172 | 39.2 | $1.22 | 86 | Compare |
| Gemini 2.0 Pro | #173 | 39.1 | — | — | Compare |
| Molmo 2 8b | #174 | 39.1 | — | — | Compare |
| Mistral Large 3 | #176 | 39.1 | $0.38 | 7 | Compare |
| GLM-4.5-Air | #177 | 38.9 | $0.43 | 160 | Compare |
| MiniMax-M2.1 | #178 | 38.9 | $0.52 | — | Compare |
| Qwen3-30B-A3B | #179 | 38.9 | $0.21 | 42 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1171 | #111 of 113, top 99% | LMArena | 2026-10-08 | |
| SciCode | 38.7% | #86 of 121, top 72% | Epoch AI | ||
| WeirdML | 43.2% | #66 of 119, top 56% | Epoch AI | ||
| LMArena Coding | 1391 | #141 of 294, top 48% | LMArena | 2026-10-08 | |
| ALE-Bench | 785.58 | #60 of 105, top 58% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| CritPt | 0.8% | #87 of 134, top 65% | Epoch AI | ||
| LMArena Hard Prompts | 1362 | #153 of 297, top 52% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Vectara Hallucination Rate (lower is better) | 12.3% | #77 of 96, top 81% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1358 | #149 of 273, top 55% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1331 | #157 of 297, top 53% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1417 | #129 of 285, top 46% | LMArena | 2026-10-08 | |
| LMArena Russian | 1304 | #174 of 283, top 62% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1329 | #158 of 298, top 54% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1330 | #164 of 291, top 57% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1355 | #154 of 297, top 52% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1289 | #175 of 295, top 60% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1358 | #150 of 295, top 51% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| inception | $0.25 | $0.75 | $0.025 | 2026-10-10 |
| openrouter | $0.25 | $0.75 | $0.025 | 2026-10-10 |
Compare Mercury 2
- Mercury 2 vs Molmo 2 8b
- Mercury 2 vs Mistral Large 3
- Mercury 2 vs Gemini 2.0 Pro
- Mercury 2 vs GLM-4.5-Air
- Mercury 2 vs Qwen3 32B
- Mercury 2 vs MiniMax-M2.1
- Mercury 2 vs GPT-6 Astra
- Mercury 2 vs Claude Fable 5.1
- Mercury 2 vs Gemini 3.8 Flash
- Mercury 2 vs Kimi K3
- Mercury 2 vs Grok 4.6
- Mercury 2 vs Qwen3.8 Max
- Mercury 2 vs GLM-5.3
- Mercury 2 vs Muse Spark 1.3
Other Inception models
- Mercury37.6
- Mercury 2.533.5
- Mercury Edit 2
Frequently asked questions
How good is Mercury 2?
Mercury 2 by Inception ranks 175th of 354 ranked models on the Noometry Index as of October 2026, with a score of 39.1. Its strongest category is long context, where it ranks 154th. API pricing starts at $0.25 per million input tokens and $0.75 per million output tokens, with a 128K-token context window.
How much does Mercury 2 cost?
Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens on Inception's own API, with cached input at $0.025.
What is Mercury 2's context window?
Mercury 2 accepts up to 128K tokens of input and can write up to 50K tokens in one response.
Is Mercury 2 open source?
No. Mercury 2 is proprietary and available only through Inception's API and partner platforms.
What are Mercury 2's strengths and weaknesses?
Relative to other ranked models, Mercury 2 places best in reasoning, writing & preference, long context and lowest in coding, knowledge, instruction following.
What is Mercury 2 best at?
Its best category is long context, where it ranks 154th on Noometry.