Inception, proprietary
Mercury 2.5
Mercury 2.5 by Inception ranks 242nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.5. Its strongest category is coding, where it ranks 156th. API pricing starts at $0.04 per million input tokens and $0.15 per million output tokens, with a 260K-token context window.
Last verified
Specifications
- Noometry rank
- #242 of 354
- Index score
- 33.5
- Evidence
- Reported 4 results
- Provider
- Inception
- Released
- September 8, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 260K
- Max output
- 66K
- Input price
- $0.04 / M
- Output price
- $0.15 / M
- Blended price
- $0.0675 / M
- Output speed
- Not measured
- Value
- #8 of 219
- Knowledge cutoff
- November 2025
- Input
- text
Category scores
Each category score combines every public result we have in that category.
- Coding 39.5
- Reasoning 22.4
- Math 23.3
Strengths and weaknesses
Categories where Mercury 2.5 places highest and lowest among the models ranked in each, with its score against that category's median.
Closest competitors
The models ranked just above and below Mercury 2.5. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Qwen3 8B | #238 | 33.7 | $0.31 | — | Compare |
| Grok-2 (Dec 2024) | #239 | 33.7 | — | — | Compare |
| GPT-4.1 mini | #240 | 33.6 | $0.70 | 86 | Compare |
| GPT-5 Nano | #241 | 33.5 | $0.14 | 4 | Compare |
| Mistral Small | #243 | 33.4 | $0.26 | 120 | Compare |
| Nova 2.0 Pro Preview | #244 | 33.4 | — | — | Compare |
| Qwen2.5-Coder-32B | #245 | 33.4 | $0.74 | — | Compare |
| Gemini 1.5 Flash (May 2024) | #246 | 33.2 | — | — | 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 |
|---|---|---|---|---|---|
| SciCode | 38.5% | #87 of 121, top 72% | Epoch AI | ||
| ALE-Bench | 301.65 | #99 of 105, top 95% | high | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| CritPt | 0% | #121 of 134, top 91% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ProofBench | 3% | #72 of 77, top 94% | Epoch AI |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| inception | $0.04 | $0.15 | $0.004 | 2026-10-10 |
| openrouter | $0.04 | $0.15 | $0.004 | 2026-10-10 |
Compare Mercury 2.5
- Mercury 2.5 vs Mercury 2
- Mercury 2.5 vs GPT-5 Nano
- Mercury 2.5 vs Mistral Small
- Mercury 2.5 vs GPT-4.1 mini
- Mercury 2.5 vs Nova 2.0 Pro Preview
- Mercury 2.5 vs Grok-2 (Dec 2024)
- Mercury 2.5 vs Qwen2.5-Coder-32B
- Mercury 2.5 vs GPT-6 Astra
- Mercury 2.5 vs Claude Fable 5.1
- Mercury 2.5 vs Gemini 3.8 Flash
- Mercury 2.5 vs Kimi K3
- Mercury 2.5 vs Grok 4.6
- Mercury 2.5 vs Qwen3.8 Max
- Mercury 2.5 vs GLM-5.3
Other Inception models
- Mercury 239.1
- Mercury37.6
- Mercury Edit 2
Frequently asked questions
How good is Mercury 2.5?
Mercury 2.5 by Inception ranks 242nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.5. Its strongest category is coding, where it ranks 156th. API pricing starts at $0.04 per million input tokens and $0.15 per million output tokens, with a 260K-token context window.
How much does Mercury 2.5 cost?
Mercury 2.5 costs $0.04 per million input tokens and $0.15 per million output tokens on Inception's own API, with cached input at $0.004.
What is Mercury 2.5's context window?
Mercury 2.5 accepts up to 260K tokens of input and can write up to 66K tokens in one response.
Is Mercury 2.5 open source?
No. Mercury 2.5 is proprietary and available only through Inception's API and partner platforms.
What are Mercury 2.5's strengths and weaknesses?
Relative to other ranked models, Mercury 2.5 places best in coding and lowest in math.
What is Mercury 2.5 best at?
Its best category is coding, where it ranks 156th on Noometry.