Data as of October 29, 2026 · How the score is built
Particle-1
Decision readingParticle-1 is tracked, but not publicly ranked yet. The profile exposes 5 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Oct 28, 2026 — see all recent releases
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.
Capability
Unranked
field median 50.5Not eligible for a public rank
Price
$0.25input / $1 output
input median $0.75cached $0.030 · blended $0.63
Speed
Not measured
field median 92 tok/sTime to first token not measured
Context
1Mtokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
5 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Source-linked · 5 displayable benchmark rows
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 |
|---|---|---|---|---|---|---|
| AgenticWeight 22%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| CodingWeight 20%2 benchmarksVerified | Score pending | 2 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeWeight 12%2 benchmarksVerified | Score pending | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
5 of 782 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow 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.
- Agentic1/1 verified
- Coding2/2 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
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 |
|---|---|---|---|---|---|
| DeepSWE | Score72.6% | Versus best verified row Best verified: Muse Wonder Full · 79.0% | Gap6.4 behind | WeightDisplay only | Provider exact |
| Terminal-Bench 2.1 | Score79.9% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap12.9 behind | WeightDisplay only | Provider exact |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score79.9% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap12.9 behind | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQA-DGPQA Diamond | Score90.4% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap5.6 behind | WeightDisplay only | Provider exact |
| MMLUMassive Multitask Language Understanding | Score86.1% | Versus best verified row Best verified: o1 · 91.8% | Gap5.7 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 5 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
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
- particle-1Particle API model catalog
- Context window
- 1MParticle API model catalog
- Maximum output
- 32,000 tokens by default; explicit limits are clamped to 131,072 tokensParticle API model catalog
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, imageParticle API model catalog
- Output modalities
- textParticle API model catalog
- Parameters
- Not disclosed by the provider
- Availability
- Particle APIParticle AI: Introducing Particle-1
- Cloud regions
- Not tracked yet
- Lifecycle
- activeParticle API model catalog
- API capabilities
- OpenAI-compatible Chat Completions, Completions and a Responses WebSocket API with mid-turn steering; streaming, tools and tool_choice, json_object output (json_schema is forwarded without a schema guarantee). Reasoning defaults to high effort, set with reasoning_effort.Particle API model catalog
- Prompt caching
- Published at $0.030 per million cached input tokensParticle API usage and billing
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
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.
We track Particle-1, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Particle-1 is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Available through the Particle API as particle-1 (public ID particle-ai/particle-1), OpenAI-compatible, with text and image input, text output, tool calling and reasoning effort control (default high). Context is 1,048,576 tokens; explicit output limits are clamped to 131,072. Particle trained a LoRA adapter on DeepSeek V4.1 Flash but has not published the adapter or a license.
Particle AI launched Particle-1 on October 28, 2026: DeepSeek V4.1 Flash post-trained with reinforcement learning to solve software engineering tasks with fewer tokens. Particle reports about 45% fewer output tokens on average with accuracy close to the base model, using a rank-64 LoRA adapter (about 1.25% of the base model's parameters) trained with GSPO in staged coding and data engineering environments. This first release targets software engineering. Coding results use the Terminus 2 agent at max reasoning, temperature 1, top-p 0.95 and a 512K-token limit, with 16 rollouts per task; Terminal-Bench 2.1 excludes the fastText task. In the same runs base DeepSeek V4.1 Flash scored 81.87 on Terminal-Bench 2.1 and 71.15 on DeepSWE 1.1. Particle also reports ReactBench and ADE-Bench pass rates, Tau Airlines and BabyVision with tools; those stay in the evidence notes because their metric or version does not match a catalog lane. The row is display-only and outside rankings.
5 of 782 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 29, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Particle-1 perform overall in AI benchmarks?
Particle-1 has 5 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Particle-1 good for knowledge and understanding?
Particle-1 has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Particle-1 good for coding and programming?
Particle-1 has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Particle-1 good for agentic tool use and computer tasks?
Particle-1 has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Does Particle-1 have full benchmark coverage on BenchLM?
No. Particle-1 currently has 5 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Particle-1?
Particle-1 has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.