Skip to main content

Model comparison

Celeris-1 vs ZAYA1-8B

Data verified

Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

Celeris
N/A
No comparison
Zyphra
N/A
1 category wins0 category wins

Evidence parity. Celeris-1 and ZAYA1-8B share 1 comparable benchmark result. 1 of 8 categories are comparable. 0 results are unique to Celeris-1; 10 to ZAYA1-8B.

Updated July 24, 2026
Shared results
1
Celeris-1 only
0
ZAYA1-8B only
10
Comparable categories
1 / 8

Treat this as a split decision. Celeris-1 makes more sense if knowledge is the priority or you would rather avoid the extra latency and token burn of a reasoning model; ZAYA1-8B is the better fit if you want the cheaper token bill or you need the larger 131K context window.

Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Celeris-1 and ZAYA1-8B finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

Celeris-1 is also the more expensive model on tokens at $2.00 input / $6.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for ZAYA1-8B. That is roughly Infinityx on output cost alone. ZAYA1-8B is the reasoning model in the pair, while Celeris-1 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. ZAYA1-8B gives you the larger context window at 131K, compared with 8K for Celeris-1.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Celeris-1 and ZAYA1-8B
CategoryCeleris-1ΔZAYA1-8B
KnowledgeCeleris-175.9Margin 2.3ZAYA1-8B73.6
MathCeleris-1Not measuredMarginNo overlapZAYA1-8B80.4
Inst. FollowingCeleris-1Not measuredMarginNo overlapZAYA1-8B64.1

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Celeris-1B · ZAYA1-8B
  1. MMLU-Pro

    Knowledge
    Source ↗
    A 75.9%B 74.2%
    Winner: Celeris-1Δ 1.7
    MMLU-Pro: Celeris-1 scored 75.9%; ZAYA1-8B scored 74.2%. Celeris-1 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricCeleris-1ZAYA1-8BComparison
Input / output priceUSD per 1M tokensCeleris-1$2 input / $6 outputZAYA1-8B$0 input / $0 outputZAYA1-8B has the lower combined listed price.
Generation speedtokens per secondCeleris-1Not availableZAYA1-8BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenCeleris-1Not availableZAYA1-8BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensCeleris-18KZAYA1-8B131KZAYA1-8B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkCeleris-1ZAYA1-8BResult
BFCL v4Source 39.2%Not comparable
Coding
BenchmarkCeleris-1ZAYA1-8BResult
LiveCodeBench v6Source 65.8%Not comparable
KnowledgeCeleris-1 wins
BenchmarkCeleris-1ZAYA1-8BResult
MMLU-ProSource 75.9%74.2%Celeris-1 leads
GPQASource 71%Not comparable
GPQA-DSource 71.0%Not comparable
Math
BenchmarkCeleris-1ZAYA1-8BResult
AIME26Source 89.1%Not comparable
HMMT Feb 2026Source 71.6%Not comparable
IMOAnswerBenchSource 59.3%Not comparable
ApexSource 32.2%Not comparable
Inst. Following
BenchmarkCeleris-1ZAYA1-8BResult
IFEvalSource 85.6%Not comparable
IFBenchSource 52.6%Not comparable
Frequently Asked Questions (2)

Which is better, Celeris-1 or ZAYA1-8B?

Celeris-1 and ZAYA1-8B are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, Celeris-1 or ZAYA1-8B?

Celeris-1 has the edge for knowledge tasks in this comparison, averaging 75.9 versus 73.6. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 24, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.