Skip to main content

Model comparison

Celeris-1 vs Soofi S 30B-A3B

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
Soofi Project
N/A
1 category wins0 category wins

Evidence parity. Celeris-1 and Soofi S 30B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 0 results are unique to Celeris-1; 7 to Soofi S 30B-A3B.

Updated July 24, 2026
Shared results
1
Celeris-1 only
0
Soofi S 30B-A3B only
7
Comparable categories
1 / 8

Treat this as a split decision. Celeris-1 makes more sense if knowledge is the priority; Soofi S 30B-A3B is the better fit if you want the cheaper token bill or you need the larger 1M 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 Soofi S 30B-A3B 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 Soofi S 30B-A3B. That is roughly Infinityx on output cost alone. Soofi S 30B-A3B gives you the larger context window at 1M, 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 Soofi S 30B-A3B
CategoryCeleris-1ΔSoofi S 30B-A3B
KnowledgeCeleris-175.9Margin 26.0Soofi S 30B-A3B49.9

Decisive benchmark drivers

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

More
A · Celeris-1B · Soofi S 30B-A3B
  1. MMLU-Pro

    Knowledge
    Source ↗
    A 75.9%B 51.4%
    Winner: Celeris-1Δ 24.5
    MMLU-Pro: Celeris-1 scored 75.9%; Soofi S 30B-A3B scored 51.4%. Celeris-1 wins this benchmark.

Operational comparison

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

MetricCeleris-1Soofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensCeleris-1$2 input / $6 outputSoofi S 30B-A3B$0 input / $0 outputSoofi S 30B-A3B has the lower combined listed price.
Generation speedtokens per secondCeleris-1Not availableSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenCeleris-1Not availableSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensCeleris-18KSoofi S 30B-A3B1MSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Coding
BenchmarkCeleris-1Soofi S 30B-A3BResult
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkCeleris-1Soofi S 30B-A3BResult
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeCeleris-1 wins
BenchmarkCeleris-1Soofi S 30B-A3BResult
MMLU-ProSource 75.9%51.4%Celeris-1 leads
GPQASource 43.4%Not comparable
GPQA-DSource 43.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkCeleris-1Soofi S 30B-A3BResult
GSM8KSource 86.1%Not comparable
Frequently Asked Questions (2)

Which is better, Celeris-1 or Soofi S 30B-A3B?

Celeris-1 and Soofi S 30B-A3B 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 Soofi S 30B-A3B?

Celeris-1 has the edge for knowledge tasks in this comparison, averaging 75.9 versus 49.9. 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.