InceptionMercury 2
Mercury 2 is an Inception proprietary reasoning model, released 20 Feb 2026. Its best configuration ranks #468 of 785 on the BenchLeader Index at 46.9 ±6.0, in the lower half. The ± is the point: 374 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (69) and lowest in coding (35). At $0.375 per million tokens blended it is cheaper than most ranked models. Output speed of 451 tokens per second puts it in the fastest quarter, with a first answer in 8.7 s. Last measured 22 Oct 2026.
- Blended price
- $0.375/M
- $0.250 in · $0.750 out
- Output speed
- 451 tok/s
- measured by Artificial Analysis
- First answer
- 8.70 s
- first token 0.69 s
- Context
- 128k
- Full answer
- 9.81 s
- median, reasoning included
- Cost per run
- $0.039
- one full Intelligence Index run
- Released
- 20 Feb 2026
- Overall index47
- Reasoning45
- Coding35
- Agents & tools44
- Knowledge39
- Instruction following69
- Human preference51
- Long context46
- Composite42
Versions
Inception has shipped 3 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| NewMercury 3high | 19 Oct 2026 | – | – |
| Mercury 2.5 | 8 Sept 2026 | 45.3 | #520 |
| Mercury 2this page | 20 Feb 2026 | 46.9 | #468 |
How its index has moved
8 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 1358#208 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 77.0%#226 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 17.1%#238 | Artificial Analysis | |
| CritPt | 0.8%#252 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode | 38.7%#173 | SciCode | |
| WeirdML | 43.2%#90 | WeirdML | |
| Arena Coding | 1392#200 | Arena (LMArena) | |
| Arena WebDev | 1171#135 | Arena (LMArena) | |
| SciCode (AA)not in index | 37.7%#191 | Artificial Analysis | |
| ALE-Benchnot in index | 785.6#76 | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 27.3%#162 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 26.5%#129 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 70.8%#154 | Artificial Analysis | |
| τ³-Banking (AA) | 9.5%#149 | Artificial Analysis | |
| AutomationBenchnot in index | 1.7%#186 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 3.8%#173 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -50.7#391 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 21.2%#287 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 8.8%#448 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 69.8%#72 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1326#211 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1343#209 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1293#224 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1342#203 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1325#236 | Arena (LMArena) |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 43.7%#344 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 10.8#373 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Inception | 318 tok/s | 0.56 s | $0.250 | $0.750 | 128k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.025 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0003 | $0.0003 | 9.4 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0035 | $0.0014 | 10.0 s |
| Code edit | 6,000 / 1,500 | $0.0026 | $0.0016 | 12.0 s |
| Agentic coding session | 60,000 / 4,000 | $0.018 | $0.0079 | 17.6 s |
| Structured extraction | 2,000 / 200 | $0.0007 | $0.0003 | 9.1 s |
More from Inception
See also
Questions people ask
- What are Mercury 2's benchmark scores?
- As of 24 Oct 2026, Mercury 2 scores 46.9 ±6.0 on the BenchLeader Index, strongest in instruction following (69) and weakest in coding (35). That rests on 13 independent benchmark results, and every score on this page links to its publisher.
- How does Mercury 2 rank?
- Mercury 2 is #468 of 785 ranked configurations on 24 Oct 2026. 374 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Mercury 2 cost per 1M tokens?
- As of 24 Oct 2026, Mercury 2 costs $0.250 per 1M input tokens and $0.750 per 1M output tokens, $0.375 blended (three input tokens per output token).
- When was Mercury 2 released?
- Inception released Mercury 2 on 20 Feb 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Mercury 2: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/mercury-2.