Capability
31.6/100
field median 57.3
#201 of 215 ranked models
Model profile · Zyphra
ZAYA1-8B
Released May 5, 2026 — see all recent releases
ZAYA1-8B scores 31.6 out of 100 and ranks #201 of 215. This profile shows 11 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #33. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Data as of August 5, 2026 · How the score is built
Strongest published evidence
Instruction Following ranks #33. A well-rounded choice across a range of tasks.
Validate before choosing
11 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 91 tok/s
Time to first token not measured
Context
131Ktokens
field median 200,000
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.
ZAYA1-8B category percentile values
- Agentic16th percentile
- CodingNot eligible
- ReasoningNot eligible
- KnowledgeNot eligible
- MathNot eligible
- MultilingualNot eligible
- MultimodalNot eligible
- Instruction following9th percentile
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#110/131
- CodingNot ranked
- ReasoningNot ranked
- KnowledgeNot ranked
- MathNot ranked
- MultilingualNot ranked
- MultimodalNot ranked
- Inst. Following#33/36
Top decileTop quartileMid-fieldNot eligible
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
- Coding1/1 verified
- ReasoningNot measured
- Knowledge3/3 verified
- Math4/4 verified
- MultilingualNot measured
- MultimodalNot measured
- Inst. Following2/2 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
- 131K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- 8B total · DENSE
- 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 |
|---|---|---|---|---|---|---|
| AgenticRank #110 of 131Percentile 16thWeight 22%1 benchmarkVerified | 39.1 | #110 of 131 | 16th | 22% | 1 benchmark | Verified |
| CodingWeight 20%1 benchmarkVerified | Score pending | Not ranked | Not available | 20% | 1 benchmark | Verified |
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | Not ranked | Not available | 17% | 0 benchmarks | Not measured |
| KnowledgeRank Not rankedWeight 12%3 benchmarksVerified | 66.0 | Not ranked | Not available | 12% | 3 benchmarks | Verified |
| MathRank Not rankedWeight 5%4 benchmarksVerified | 61.9 | Not ranked | Not available | 5% | 4 benchmarks | 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 #33 of 36Percentile 9thWeight 5%2 benchmarksVerified | 31.6 | #33 of 36 | 9th | 5% | 2 benchmarks | 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.
Coding1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| LiveCodeBench v6 | Score65.8% | Versus best verified row Best verified: Sakana Fugu-Ultra · 93.2% | Gap27.4 behind | WeightDisplay only | Provider exact |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BFCL v4Berkeley Function Calling Leaderboard v4 | Score39.2% | Versus best verified row Best verified: Qwen3.7 Max · 75.0% | Gap35.8 behind | WeightDisplay only | Provider exact |
Knowledge3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | Score74.2% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap15.4 behind | WeightWeighted 30% | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score71% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | Gap24.5 behind | WeightWeighted 7% | Provider exact |
| GPQA-DGPQA Diamond | Score71.0% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | Gap24.5 behind | WeightDisplay only | Provider exact |
Math4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME26AIME 2026 | Score89.1% | Versus best verified row Best verified: GLM-5.2 · 99.2% | Gap10.1 behind | WeightWeighted 25% | Provider exact |
| HMMT Feb 2026Harvard-MIT Mathematics Tournament February 2026 | Score71.6% | Versus best verified row Best verified: Qwen3.7 Max · 97.1% | Gap25.5 behind | WeightWeighted 25% | Provider exact |
| IMOAnswerBench | Score59.3% | Versus best verified row Best verified: Qwen3.7 Max · 90.0% | Gap30.7 behind | WeightDisplay only | Provider exact |
| Apex | Score32.2% | Versus best verified row Best verified: Qwen3.7 Max · 44.5% | Gap12.3 behind | WeightDisplay only | Provider exact |
Inst. Following2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | Score52.6% | Versus best verified row Best verified: MAI-Thinking-1 · 85% | Gap32.4 behind | WeightWeighted 65% | Provider exact |
| IFEvalInstruction-Following Eval | Score85.6% | Versus best verified row Best verified: Qwen3.5-27B · 95% | Gap9.4 behind | WeightWeighted 35% | 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 5, 2026 · you are here
ZAYA1-8BScore 31.6 · Price not listed
8b
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.
ZAYA1-8B ranks #201 of 215 on the public leaderboard with a score of 31.58/100. It does not yet have enough sourced coverage for a verified position.
ZAYA1-8B is a open weight model with a 131K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official exact-value snapshot from Zyphra's May 5, 2026 ZAYA1-8B launch post and matching Hugging Face model card. BenchLM maps GPQA-Diamond onto both the weighted GPQA lane and display GPQA-Diamond lane for category comparability, while LiveCodeBench-v6 and other provider-specific slices remain on display-only keys where they do not match the weighted schema.
ZAYA1-8B sits in the ZAYA1 family with ZAYA1-74B-Preview. 11 of 381 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #33, while its lowest eligible position is Agentic at #110. a well-rounded choice across a range of tasks.
Radar
Full release historyZAYA1-8B release history
ZAYA1-8B released
Zyphra · Model release
Source confirmed
Frequently asked questions
How does ZAYA1-8B perform overall in AI benchmarks?
ZAYA1-8B ranks #201 out of 215 models on the public BenchAlign leaderboard, with a score of 31.58/100. Its evidence status is Estimated, and this profile shows 11 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is ZAYA1-8B good for knowledge and understanding?
ZAYA1-8B 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 ZAYA1-8B good for coding and programming?
ZAYA1-8B 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 ZAYA1-8B good for mathematics?
ZAYA1-8B 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 ZAYA1-8B good for agentic tool use and computer tasks?
ZAYA1-8B ranks #110 out of 131 eligible models for agentic tool use and computer tasks, with a public category score of 39.1/100. 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 ZAYA1-8B good for instruction following?
ZAYA1-8B ranks #33 out of 36 eligible models for instruction following, with a public category score of 31.6/100. 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 ZAYA1-8B open source?
ZAYA1-8B 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 ZAYA1-8B?
ZAYA1-8B belongs to the ZAYA1 family. Related tracked variants include ZAYA1-74B-Preview. 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 ZAYA1-8B have full benchmark coverage on BenchLM?
No. ZAYA1-8B currently has 11 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 ZAYA1-8B?
ZAYA1-8B has a reported context window of 131K 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 5, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch ZAYA1-8B 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.