Capability
42.3/100
field median 56.3
#161 of 231 ranked models
Mercury 2 model card
Released Feb 24, 2026 — see all recent releases
Decision reading
Mercury 2 remains supported for existing customers. Inception released its successor, Mercury 2.5, on September 8, 2026 with a 260K context window and launch pricing of $0.04 per million input tokens and $0.15 per million output tokens. The benchmark ledger on this page belongs to Mercury 2; the successor has its own model record.
Data as of September 10, 2026 · How the score is built
Share or export
Strongest published evidence
Agentic ranks #124. Particularly useful for coding agents, browser research, and computer-use workflows.
Validate before choosing
9 published rows leave some tracked benchmark slots empty. Coding is its lowest eligible category at #149.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
$0.25input / $0.75 output
input median $1
cached $0.025 · blended $0.50
Speed
925tok/s
field median 92 tok/s
First token 4.17 s
Context
128Ktokens
field median 256,000
Reported for this model; direct source link not stored
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Mercury 2 category percentile values
- Agentic19th percentile
- Coding1st percentile
- ReasoningNot eligible
- KnowledgeNot eligible
- MathNot eligible
- MultilingualNot eligible
- MultimodalNot eligible
- Instruction followingNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#124/152
- Coding#149/151
- ReasoningNot ranked
- KnowledgeNot ranked
- MathNot ranked
- MultilingualNot ranked
- MultimodalNot ranked
- Inst. FollowingNot ranked
Top decileTop quartileMid-fieldNot eligible
What it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Current modelMercury 2 · 42.3 score · $0.50 blended per million tokens
Horizontal: blended price per million tokens, log scale · Vertical: public score
How much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic3/3 verified
- Coding2/2 verified
- ReasoningNot measured
- Knowledge2/2 verified
- Math1/1 verified
- MultilingualNot measured
- MultimodalNot measured
- Inst. Following1/1 verified
Verified sourceProvisionalNot measured
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 128K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Mercury 2 remains supported for existing customers. Inception’s September 8, 2026 models page directs customers to their representative or documentation for access and migration to Mercury 2.5.
- Cloud regions
- Not tracked yet
- Lifecycle
- Superseded
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.025 per million cached input tokens
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #124 of 152Percentile 19thWeight 22%3 benchmarksVerified | 38.1 | #124 of 152 | 19th | 22% | 3 benchmarks | Verified |
| CodingRank #149 of 151Percentile 1stWeight 20%2 benchmarksVerified | 24.6 | #149 of 151 | 1st | 20% | 2 benchmarks | Verified |
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | Not ranked | Not available | 17% | 0 benchmarks | Not measured |
| KnowledgeRank Not rankedWeight 12%2 benchmarksVerified | 58.5 | Not ranked | Not available | 12% | 2 benchmarks | Verified |
| MathWeight 5%1 benchmarkVerified | Score pending | Not ranked | Not available | 5% | 1 benchmark | Verified |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| Inst. FollowingRank Not rankedWeight 5%1 benchmarkVerified | 70.9 | Not ranked | Not available | 5% | 1 benchmark | Verified |
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| LiveCodeBenchLiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code | Score67.3% | Versus best verified row Best verified: Qwen3.7 Max · 91.6% | Gap24.3 behind | WeightWeighted 15% | Provider exact |
| SciCodeScientific Code Benchmark | Score38.4% | Versus best verified row Best verified: Sakana Fugu · 60.1% | Gap21.7 behind | WeightWeighted 10% | Provider exact |
Agentic3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| PinchBench | Score78.0% | Versus best verified row Best verified: Pokee-Isaac 28B · 95.7% | Gap17.7 behind | WeightDisplay only | Provider exact |
| DeepSearchQA | Score34.0% | Versus best verified row Best verified: Claude Opus 5 · 95.0% | Gap61 behind | WeightDisplay only | Provider exact |
| WideResearch | Score92.3% | Versus best verified row Best verified: Hy4 preview · 83.9% | Gap8.4 behind | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQAGraduate-Level Google-Proof Q&A | Score73.6% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap22.4 behind | WeightWeighted 7% | Provider exact |
| GPQA-DGPQA Diamond | Score73.6% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap22.4 behind | WeightDisplay only | Provider exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME 2025American Invitational Mathematics Examination 2025 | Score91.1% | Versus best verified row Best verified: MAI-Thinking-1 · 97% | Gap5.9 behind | WeightDisplay only | Provider exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | Score71.3% | Versus best verified row Best verified: MAI-Thinking-1 · 85% | Gap13.7 behind | WeightWeighted 70% | Provider exact |
Lineage
The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Feb 24, 2026 · you are here
Mercury 2Score 42.3 · $0.25 / $0.75
Sep 8, 2026
Mercury 2.5Not publicly ranked · $0.04 / $0.15
Aug 31, 2026
Mercury 2.5 PreviewNot publicly ranked · Price not listed
Base entry
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Mercury 2 ranks #161 of 231 on the public leaderboard with a score of 42.34/100. Its source-verified position is #93 of 130.
Mercury 2 is a proprietary model with a 128K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Mercury 2 remains supported for existing customers. Inception’s September 8, 2026 models page directs customers to their representative or documentation for access and migration to Mercury 2.5.
Inception released Mercury 2 on February 24, 2026 as a proprietary diffusion reasoning model. Its launch materials report AIME 2025, GPQA, IFBench, LiveCodeBench, SciCode, PinchBench, DeepSearchQA, and a fresh-facts WideSearch run. Those source-backed values replace their earlier entries; all remaining historical rows are retained pending primary-source verification. Independently run display rows remain separate and do not influence ranking.
9 of 428 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Agentic at #124, while its lowest eligible position is Coding at #149. particularly useful for coding agents, browser research, and computer-use workflows.
Model research
Mercury 2.5 is now available
Inception’s September 8 launch introduces Mercury 2.5 with 260K context, tunable reasoning, parallel tool calls, and schema-aligned JSON. Its published standard rates are $0.20 per million input tokens and $0.75 per million output tokens; the launch offer reduces those to $0.04 and $0.15. Cached input is $0.004 during the offer.
The models page says Mercury 2 remains supported for existing customers. Ask Inception for access or migration guidance. We keep the two generations separate so Mercury 2.5 results cannot be mistaken for a new measurement of Mercury 2.
What Mercury 2 is built for
Inception released Mercury 2 on February 24, 2026 as a proprietary diffusion reasoning model. It accepts text, returns text, exposes a 128K context window, and supports tunable reasoning, tool use, schema-aligned JSON, and an OpenAI-compatible chat-completions interface.
The intended fit is latency-sensitive text work that can benefit from high sustained output: agent steps, search synthesis, coding, structured extraction, and the reasoning layer inside a cascaded voice system. Mercury 2 is not a native audio model; voice applications still need speech recognition and speech generation around it.
How to read the speed evidence
The current hosted runtime row measures Mercury 2 at 925 output tokens per second and 4.17 seconds to the first answer. Inception separately reports 1,009 tokens per second on NVIDIA Blackwell. The workloads, hardware, and timing methods differ, so the provider number remains separate from the cross-provider row.
Output rate and first-answer delay measure different parts of a request. Mercury can produce a long response quickly after generation begins while still making a user wait longer for the initial chunk than another model. Voice teams should measure end-of-speech to first audible output across the complete speech stack.
Quality evidence is sourced, but mostly provider-run
Official API pricing is $0.25 per million input tokens, $0.025 per million cached input tokens, and $0.75 per million output tokens. Inception documents the 128K window, reasoning controls, tool use, and structured output on the same first-party release page.
Mercury 2 now has source-attached results for GPQA, LiveCodeBench, SciCode, AIME 2025, IFBench, PinchBench, DeepSearchQA, and WideSearch. Most are provider-run, so the profile links each published row to its exact source and keeps unsupported historical rows hidden. The public score uses only evidence admitted by the ranking pipeline.
Radar
Full release historyMercury 2 release history
Mercury 2 released
Inception · Model release
Source confirmed
Radar confirmed these at the source. Use Mercury 2 in your work? Explore Radar to follow supported changes and choose your alerts.
Frequently asked questions
What is Mercury 2?
Mercury 2 is Inception’s proprietary diffusion reasoning model, released February 24, 2026. It accepts and returns text, has a 128K context window, and supports adjustable reasoning, tool use, schema-aligned JSON, and an OpenAI-compatible chat-completions interface. It is served as an API rather than released as open weights.
How much does the Mercury 2 API cost?
Inception lists Mercury 2 at $0.25 per million input tokens, $0.025 per million cached input tokens, and $0.75 per million output tokens. Those are first-party API rates. A production bill also depends on prompt size, reasoning output, retries, tools, and any speech or retrieval services around the model.
How fast is Mercury 2?
The current hosted runtime row measures Mercury 2 at 925 output tokens per second and 4.17 seconds to the first answer. Inception separately reports 1,009 tokens per second on NVIDIA Blackwell. Different workloads and timing boundaries mean the two figures are complementary measurements, not a failed replication.
Is Mercury 2 a diffusion LLM?
Yes. Inception describes Mercury 2 as a diffusion language model that refines multiple token positions across denoising steps rather than relying only on left-to-right token generation. The hosted weights and complete training specification are not public, so the architecture description remains first-party rather than independently inspected.
Does Mercury 2 support tool use and structured output?
Yes. Inception documents tool use, schema-aligned JSON, adjustable reasoning, and OpenAI-compatible chat completions. Applications should still validate schemas, permissions, and tool arguments outside the model. The public evidence does not yet establish a verified tool-use benchmark, so feature support should not be read as measured reliability.
Is Mercury 2 good for voice agents?
Mercury 2 can serve as the text reasoning layer in a cascaded voice agent, but it does not accept or return native audio. Teams must add speech recognition, text-to-speech, turn detection, and transport. Compare full end-of-speech to first-audio latency against native models instead of treating text throughput as voice latency.
Compare Mercury 2 with every tracked model412 comparisons
Last updated September 10, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch Mercury 2 in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.