Capability
Unranked
field median 57.5
Not eligible for a public rank
Model profile · Zyphra
ZAYA1-74B-Preview
Released May 7, 2026 — see all recent releases
ZAYA1-74B-Preview is tracked, but not publicly ranked yet. The profile exposes 7 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Data as of August 7, 2026 · How the score is built
Strongest published evidence
Coding ranks #74. Particularly well-suited for software development and code generation tasks.
Validate before choosing
7 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
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
Self-hosted; infrastructure cost varies
input median $1
No comparable first-party hosted token rate
Speed
Not measured
field median 89 tok/s
Time to first token not measured
Context
256Ktokens
field median 201,500
Reported for this model; direct source link not stored
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.
- Agentic1/1 verified
- Coding2/2 verified
- ReasoningNot measured
- Knowledge3/3 verified
- Math1/1 verified
- MultilingualNot measured
- MultimodalNot measured
- Inst. FollowingNot measured
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
- 256K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersCategory 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 | Not ranked | Not available | 22% | 1 benchmark | Verified |
| CodingRank #74 of 132Percentile 44thWeight 20%2 benchmarksVerified | 48.2 | #74 of 132 | 44th | 20% | 2 benchmarks | Verified |
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | Not ranked | Not available | 17% | 0 benchmarks | Not measured |
| KnowledgeRank Not rankedWeight 12%3 benchmarksVerified | 57.6 | Not ranked | Not available | 12% | 3 benchmarks | Verified |
| MathRank Not rankedWeight 5%1 benchmarkVerified | 56.5 | 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. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not 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 |
|---|---|---|---|---|---|
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score53.2% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap42.8 behind | WeightWeighted 16% | Provider exact |
| LiveCodeBench v6 | Score65.7% | Versus best verified row Best verified: Sakana Fugu-Ultra · 93.2% | Gap27.5 behind | WeightDisplay only | Provider exact |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| τ²-bench Airlineτ²-Bench Airline Domain | Score56.1% | Versus best verified row Best verified: ZAYA1-74B-Preview · 56.1% | GapBest verified | WeightDisplay only | Provider exact |
Knowledge3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | Score68.1% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap21.5 behind | WeightWeighted 30% | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score57.3% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | Gap38.2 behind | WeightWeighted 7% | Provider exact |
| GPQA-DGPQA Diamond | Score57.3% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | Gap38.2 behind | WeightDisplay only | Provider exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME26AIME 2026 | Score76.4% | Versus best verified row Best verified: GLM-5.2 · 99.2% | Gap22.8 behind | WeightWeighted 25% | Provider exact |
Lineage
The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
May 7, 2026 · you are here
ZAYA1-74B-PreviewNot publicly ranked · Price not listed
74b-preview · preview
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 ZAYA1-74B-Preview, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
ZAYA1-74B-Preview is a open weight model with a 256K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official chart snapshot from Zyphra's May 7, 2026 ZAYA1-74B-Preview launch post and matching Hugging Face model card. Zyphra describes this as a pre-RL reasoning-base checkpoint with 74B total and 4B active parameters, not a chat-tuned or RL-post-trained model. BenchLM maps Zyphra's avg@1 chart values to comparable rows and leaves pass@4 rows out of ranking/display until BenchLM has explicit pass@k lanes.
ZAYA1-74B-Preview sits in the ZAYA1 family with ZAYA1-8B. 7 of 381 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Coding at #74. particularly well-suited for software development and code generation tasks.
Radar
Full release historyZAYA1-74B-Preview release history
ZAYA1-74B-Preview released
Zyphra · Model release
Source confirmed
Frequently asked questions
How does ZAYA1-74B-Preview perform overall in AI benchmarks?
ZAYA1-74B-Preview has 7 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 ZAYA1-74B-Preview good for knowledge and understanding?
ZAYA1-74B-Preview 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 ZAYA1-74B-Preview good for coding and programming?
ZAYA1-74B-Preview ranks #74 out of 132 eligible models for coding and programming, with a public category score of 48.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is ZAYA1-74B-Preview good for mathematics?
ZAYA1-74B-Preview has source-displayable benchmark coverage for mathematics, 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 ZAYA1-74B-Preview good for agentic tool use and computer tasks?
ZAYA1-74B-Preview 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.
Is ZAYA1-74B-Preview open source?
ZAYA1-74B-Preview is an open-weight model from Zyphra. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to ZAYA1-74B-Preview?
ZAYA1-74B-Preview belongs to the ZAYA1 family. Related tracked variants include ZAYA1-8B. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does ZAYA1-74B-Preview have full benchmark coverage on BenchLM?
No. ZAYA1-74B-Preview currently has 7 source-displayable rows across 381 tracked benchmark slots. 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 ZAYA1-74B-Preview?
ZAYA1-74B-Preview has a reported context window of 256K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.
Last updated August 7, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch ZAYA1-74B-Preview 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.