Skip to main content

Model comparison

o1 vs Qwen3.5-35B-A3B

Data verified

Head-to-head evidence from 13 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

OpenAI
48.1/100
Margin
8.9pts
winning →
56.97/100
1 category wins1 category wins

Public leaderboard positions: o1 #129 (Estimated); Qwen3.5-35B-A3B #72 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. o1 and Qwen3.5-35B-A3B share 13 comparable benchmark results. 2 of 8 categories are comparable. 3 results are unique to o1; 15 to Qwen3.5-35B-A3B.

Updated July 23, 2026
Shared results
13
o1 only
3
Qwen3.5-35B-A3B only
15
Comparable categories
2 / 8

Pick Qwen3.5-35B-A3B if you want the stronger benchmark profile. o1 only becomes the better choice if instruction following is the priority.

Confidence note. This is a partial-evidence comparison with 13 shared benchmark results across 5 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.5-35B-A3B is clearly ahead on the BenchAlign aggregate, 56.97 to 48.1. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.5-35B-A3B's sharpest advantage is in knowledge, where it averages 81.6 against 75.7. The single biggest benchmark swing on the page is GPQA, 75.7% to 84.2%. o1 does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.

o1 is also the more expensive model on tokens at $15.00 input / $60.00 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 gives you the larger context window at 262K, compared with 200K for o1.

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 o1 and Qwen3.5-35B-A3B
Categoryo1ΔQwen3.5-35B-A3B
Knowledgeo175.7Margin 5.9Qwen3.5-35B-A3B81.6
Inst. Followingo192.2Margin 0.3Qwen3.5-35B-A3B91.9
Agentico1Not measuredMarginNo overlapQwen3.5-35B-A3B51.0
Codingo1Not measuredMarginNo overlapQwen3.5-35B-A3B60.6
Reasoningo1Not measuredMarginNo overlapQwen3.5-35B-A3B59.0
Matho19.3MarginNo overlapQwen3.5-35B-A3BNot measured
Multilingualo1Not measuredMarginNo overlapQwen3.5-35B-A3B81.0

Decisive benchmark drivers

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

More
A · o1B · Qwen3.5-35B-A3B
  1. GPQA

    Knowledge
    Source ↗
    A 75.7%B 84.2%
    Winner: Qwen3.5-35B-A3BΔ 8.5
    GPQA: o1 scored 75.7%; Qwen3.5-35B-A3B scored 84.2%. Qwen3.5-35B-A3B wins this benchmark.
  2. IFEval

    Inst. Following
    Source ↗
    A 92.2%B 91.9%
    Winner: o1Δ 0.3
    IFEval: o1 scored 92.2%; Qwen3.5-35B-A3B scored 91.9%. o1 wins this benchmark.

Operational comparison

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

Metrico1Qwen3.5-35B-A3BComparison
Input / output priceUSD per 1M tokenso1$15 input / $60 outputQwen3.5-35B-A3B$0 input / $0 outputQwen3.5-35B-A3B has the lower combined listed price.
Generation speedtokens per secondo198 tok/sQwen3.5-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokeno132.29 sQwen3.5-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokenso1200KQwen3.5-35B-A3B262KQwen3.5-35B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
Benchmarko1Qwen3.5-35B-A3BResult
τ²-bench resultsSource 62.6%89.2%Qwen3.5-35B-A3B leads
Terminal-Bench 2.0Source 40.5%Not comparable
BrowseCompSource 61%Not comparable
OSWorld-VerifiedSource 54.5%Not comparable
Gert LabsSource 28.96%Not comparable
Coding
Benchmarko1Qwen3.5-35B-A3BResult
AA Coding IndexSource 39.7%Not comparable
AA-SciCodeSource 35.8%37.7%Qwen3.5-35B-A3B leads
SWE-bench VerifiedSource 69.2%Not comparable
SWE-RebenchSource 53.7%Not comparable
Reasoning
Benchmarko1Qwen3.5-35B-A3BResult
AA-LCRSource 59.3%62.7%Qwen3.5-35B-A3B leads
CritPtSource 0.3%0.9%Qwen3.5-35B-A3B leads
LongBench v2Source 59%Not comparable
KnowledgeQwen3.5-35B-A3B wins
Benchmarko1Qwen3.5-35B-A3BResult
MMLUSource 91.8%Not comparable
GPQASource 75.7%84.2%Qwen3.5-35B-A3B leads
Artificial Analysis Intelligence IndexSource 23.4%29.3%Qwen3.5-35B-A3B leads
AA-GPQA DiamondSource 74.7%84.5%Qwen3.5-35B-A3B leads
AA-HLESource 7.7%19.7%Qwen3.5-35B-A3B leads
AA-Omniscience IndexSource -10.5%-46.4%o1 leads
AA-Omniscience AccuracySource 34.7%20.5%o1 leads
AA-Omniscience Hallucination RateSource 69.3%84.0%o1 leads
MMLU-ProSource 85.3%Not comparable
SuperGPQASource 63.4%Not comparable
Math
Benchmarko1Qwen3.5-35B-A3BResult
FrontierMath v2 (Tiers 1-3)Source 9.310%Not comparable
Multilingual
Benchmarko1Qwen3.5-35B-A3BResult
MMLU-ProXSource 81%Not comparable
Multimodal
Benchmarko1Qwen3.5-35B-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. Followingo1 wins
Benchmarko1Qwen3.5-35B-A3BResult
IFEvalSource 92.2%91.9%o1 leads
AA-IFBenchSource 70.3%72.5%Qwen3.5-35B-A3B leads
Frequently Asked Questions (3)

Which is better, o1 or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B is ahead on BenchLM's BenchAlign leaderboard, 56.97 to 48.1. The biggest single separator in this matchup is GPQA, where the scores are 75.7% and 84.2%.

Which is better for knowledge tasks, o1 or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 75.7. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for instruction following, o1 or Qwen3.5-35B-A3B?

o1 has the edge for instruction following in this comparison, averaging 92.2 versus 91.9. Inside this category, AA-IFBench is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 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.