Skip to main content

Model comparison

Celeris-1 vs Qwen3.5-35B-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
56.97/100
0 category wins1 category wins

Public leaderboard positions: Celeris-1 unranked (Not scored); Qwen3.5-35B-A3B #72 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Celeris-1 and Qwen3.5-35B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 0 results are unique to Celeris-1; 27 to Qwen3.5-35B-A3B.

Updated July 24, 2026
Shared results
1
Celeris-1 only
0
Qwen3.5-35B-A3B only
27
Comparable categories
1 / 8

Treat this as a split decision. Celeris-1 makes more sense if you would rather avoid the extra latency and token burn of a reasoning model; Qwen3.5-35B-A3B is the better fit if knowledge is the priority or you want the cheaper token bill.

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 Qwen3.5-35B-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 Qwen3.5-35B-A3B. That is roughly Infinityx on output cost alone. Qwen3.5-35B-A3B 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. Qwen3.5-35B-A3B gives you the larger context window at 262K, 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 Qwen3.5-35B-A3B
CategoryCeleris-1ΔQwen3.5-35B-A3B
KnowledgeCeleris-175.9Margin 5.7Qwen3.5-35B-A3B81.6
AgenticCeleris-1Not measuredMarginNo overlapQwen3.5-35B-A3B51.0
CodingCeleris-1Not measuredMarginNo overlapQwen3.5-35B-A3B60.6
ReasoningCeleris-1Not measuredMarginNo overlapQwen3.5-35B-A3B59.0
MultilingualCeleris-1Not measuredMarginNo overlapQwen3.5-35B-A3B81.0
Inst. FollowingCeleris-1Not measuredMarginNo overlapQwen3.5-35B-A3B91.9

Decisive benchmark drivers

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

More
A · Celeris-1B · Qwen3.5-35B-A3B
  1. MMLU-Pro

    Knowledge
    Source ↗
    A 75.9%B 85.3%
    Winner: Qwen3.5-35B-A3BΔ 9.4
    MMLU-Pro: Celeris-1 scored 75.9%; Qwen3.5-35B-A3B scored 85.3%. Qwen3.5-35B-A3B wins this benchmark.

Operational comparison

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

MetricCeleris-1Qwen3.5-35B-A3BComparison
Input / output priceUSD per 1M tokensCeleris-1$2 input / $6 outputQwen3.5-35B-A3B$0 input / $0 outputQwen3.5-35B-A3B has the lower combined listed price.
Generation speedtokens per secondCeleris-1Not availableQwen3.5-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenCeleris-1Not availableQwen3.5-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensCeleris-18KQwen3.5-35B-A3B262KQwen3.5-35B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkCeleris-1Qwen3.5-35B-A3BResult
Terminal-Bench 2.0Source 40.5%Not comparable
BrowseCompSource 61%Not comparable
OSWorld-VerifiedSource 54.5%Not comparable
τ²-bench resultsSource 89.2%Not comparable
Gert LabsSource 28.96%Not comparable
Coding
BenchmarkCeleris-1Qwen3.5-35B-A3BResult
SWE-bench VerifiedSource 69.2%Not comparable
SWE-RebenchSource 53.7%Not comparable
AA-SciCodeSource 37.7%Not comparable
Reasoning
BenchmarkCeleris-1Qwen3.5-35B-A3BResult
LongBench v2Source 59%Not comparable
AA-LCRSource 62.7%Not comparable
CritPtSource 0.9%Not comparable
KnowledgeQwen3.5-35B-A3B wins
BenchmarkCeleris-1Qwen3.5-35B-A3BResult
MMLU-ProSource 75.9%85.3%Qwen3.5-35B-A3B leads
SuperGPQASource 63.4%Not comparable
GPQASource 84.2%Not comparable
Artificial Analysis Intelligence IndexSource 29.3%Not comparable
AA-GPQA DiamondSource 84.5%Not comparable
AA-HLESource 19.7%Not comparable
AA-Omniscience IndexSource -46.4%Not comparable
AA-Omniscience AccuracySource 20.5%Not comparable
AA-Omniscience Hallucination RateSource 84.0%Not comparable
Multilingual
BenchmarkCeleris-1Qwen3.5-35B-A3BResult
MMLU-ProXSource 81%Not comparable
Multimodal
BenchmarkCeleris-1Qwen3.5-35B-A3BResult
MMMUSource 81.4%Not comparable
MMVUSource 72.3%Not comparable
MathVisionSource 83.9%Not comparable
V*Source 92.7%Not comparable
AA-MMMU-ProSource 72.7%Not comparable
Inst. Following
BenchmarkCeleris-1Qwen3.5-35B-A3BResult
IFEvalSource 91.9%Not comparable
AA-IFBenchSource 72.5%Not comparable
Frequently Asked Questions (2)

Which is better, Celeris-1 or Qwen3.5-35B-A3B?

Celeris-1 and Qwen3.5-35B-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 Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 75.9. 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.