Skip to main content

Model comparison

GPT-4.1 mini vs Qwen3.5-35B-A3B

Data verified

Head-to-head evidence from 15 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

44.19/100
Margin
12.8pts
winning →
56.97/100
0 category wins3 category wins

Public leaderboard positions: GPT-4.1 mini #152 (Estimated); Qwen3.5-35B-A3B #72 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-4.1 mini and Qwen3.5-35B-A3B share 15 comparable benchmark results. 3 of 8 categories are comparable. 7 results are unique to GPT-4.1 mini; 13 to Qwen3.5-35B-A3B.

Updated July 23, 2026
Shared results
15
GPT-4.1 mini only
7
Qwen3.5-35B-A3B only
13
Comparable categories
3 / 8

Pick Qwen3.5-35B-A3B if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if you need the larger 1M context window or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 15 shared benchmark results across 6 evidence categories; 3 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 44.19. 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 coding, where it averages 60.6 against 23.6. The single biggest benchmark swing on the page is SWE-bench Verified, 23.6% to 69.2%.

GPT-4.1 mini is also the more expensive model on tokens at $0.40 input / $1.60 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 GPT-4.1 mini 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. GPT-4.1 mini gives you the larger context window at 1M, compared with 262K for Qwen3.5-35B-A3B.

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 GPT-4.1 mini and Qwen3.5-35B-A3B
CategoryGPT-4.1 miniΔQwen3.5-35B-A3B
CodingGPT-4.1 mini23.6Margin 37.0Qwen3.5-35B-A3B60.6
KnowledgeGPT-4.1 mini64.2Margin 17.4Qwen3.5-35B-A3B81.6
Inst. FollowingGPT-4.1 mini88.5Margin 3.4Qwen3.5-35B-A3B91.9
AgenticGPT-4.1 miniNot measuredMarginNo overlapQwen3.5-35B-A3B51.0
ReasoningGPT-4.1 miniNot measuredMarginNo overlapQwen3.5-35B-A3B59.0
MathGPT-4.1 mini4.5MarginNo overlapQwen3.5-35B-A3BNot measured
MultilingualGPT-4.1 miniNot measuredMarginNo overlapQwen3.5-35B-A3B81.0

Decisive benchmark drivers

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

More
A · GPT-4.1 miniB · Qwen3.5-35B-A3B
  1. SWE-bench Verified

    Coding
    Source ↗
    A 23.6%B 69.2%
    Winner: Qwen3.5-35B-A3BΔ 45.6
    SWE-bench Verified: GPT-4.1 mini scored 23.6%; Qwen3.5-35B-A3B scored 69.2%. Qwen3.5-35B-A3B wins this benchmark.
  2. GPQA

    Knowledge
    Source ↗
    A 64.2%B 84.2%
    Winner: Qwen3.5-35B-A3BΔ 20
    GPQA: GPT-4.1 mini scored 64.2%; Qwen3.5-35B-A3B scored 84.2%. Qwen3.5-35B-A3B wins this benchmark.
  3. IFEval

    Inst. Following
    Source ↗
    A 88.5%B 91.9%
    Winner: Qwen3.5-35B-A3BΔ 3.4
    IFEval: GPT-4.1 mini scored 88.5%; Qwen3.5-35B-A3B scored 91.9%. Qwen3.5-35B-A3B wins this benchmark.

Operational comparison

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

MetricGPT-4.1 miniQwen3.5-35B-A3BComparison
Input / output priceUSD per 1M tokensGPT-4.1 mini$0.4 input / $1.6 outputQwen3.5-35B-A3B$0 input / $0 outputQwen3.5-35B-A3B has the lower combined listed price.
Generation speedtokens per secondGPT-4.1 mini80 tok/sQwen3.5-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-4.1 mini0.76 sQwen3.5-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-4.1 mini1MQwen3.5-35B-A3B262KGPT-4.1 mini lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
AA Agentic IndexSource 1.7%Not comparable
τ²-bench resultsSource 52.9%89.2%Qwen3.5-35B-A3B leads
GDPval-AASource 0.1%Not comparable
GDPval-AASource 503Not comparable
Terminal-Bench 2.0Source 40.5%Not comparable
BrowseCompSource 61%Not comparable
OSWorld-VerifiedSource 54.5%Not comparable
Gert LabsSource 28.96%Not comparable
CodingQwen3.5-35B-A3B wins
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
SWE-bench VerifiedSource 23.6%69.2%Qwen3.5-35B-A3B leads
AA Coding IndexSource 20.2%Not comparable
AA-SciCodeSource 40.4%37.7%GPT-4.1 mini leads
SWE-RebenchSource 53.7%Not comparable
Reasoning
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
AA-LCRSource 42.3%62.7%Qwen3.5-35B-A3B leads
CritPtSource 0.0%0.9%Qwen3.5-35B-A3B leads
LongBench v2Source 59%Not comparable
KnowledgeQwen3.5-35B-A3B wins
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
MMLUSource 87.5%Not comparable
GPQASource 64.2%84.2%Qwen3.5-35B-A3B leads
Artificial Analysis Intelligence IndexSource 14.8%29.3%Qwen3.5-35B-A3B leads
AA-GPQA DiamondSource 66.4%84.5%Qwen3.5-35B-A3B leads
AA-HLESource 4.6%19.7%Qwen3.5-35B-A3B leads
AA-Omniscience IndexSource -50.1%-46.4%Qwen3.5-35B-A3B leads
AA-Omniscience AccuracySource 17.5%20.5%Qwen3.5-35B-A3B leads
AA-Omniscience Hallucination RateSource 82.0%84.0%GPT-4.1 mini leads
MMLU-ProSource 85.3%Not comparable
SuperGPQASource 63.4%Not comparable
Math
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
FrontierMath v2 (Tiers 1-3)Source 4.483%Not comparable
Multilingual
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
MMLU-ProXSource 81%Not comparable
Multimodal
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
AA-MMMU-ProSource 58.7%72.7%Qwen3.5-35B-A3B leads
Design Arena WebsiteSource 1027Not comparable
MMMUSource 81.4%Not comparable
MMVUSource 72.3%Not comparable
MathVisionSource 83.9%Not comparable
V*Source 92.7%Not comparable
Inst. FollowingQwen3.5-35B-A3B wins
BenchmarkGPT-4.1 miniQwen3.5-35B-A3BResult
IFEvalSource 88.5%91.9%Qwen3.5-35B-A3B leads
AA-IFBenchSource 38.3%72.5%Qwen3.5-35B-A3B leads
Frequently Asked Questions (4)

Which is better, GPT-4.1 mini or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B is ahead on BenchLM's BenchAlign leaderboard, 56.97 to 44.19. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 23.6% and 69.2%.

Which is better for knowledge tasks, GPT-4.1 mini or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 64.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-4.1 mini or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for coding in this comparison, averaging 60.6 versus 23.6. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-4.1 mini or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for instruction following in this comparison, averaging 91.9 versus 88.5. 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.