Skip to main content

Model comparison

Gemini 2.5 Pro vs GPT-4.1 mini

Data verified

Head-to-head evidence from 20 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.66/100
Margin
13.6pts
← winning
43.1/100
2 category wins1 category wins

Public leaderboard positions: Gemini 2.5 Pro #75 (Supported); GPT-4.1 mini #160 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemini 2.5 Pro and GPT-4.1 mini share 20 comparable benchmark results. 3 of 8 categories are comparable. 4 results are unique to Gemini 2.5 Pro; 2 to GPT-4.1 mini.

Updated July 24, 2026
Shared results
20
Gemini 2.5 Pro only
4
GPT-4.1 mini only
2
Comparable categories
3 / 8

Pick Gemini 2.5 Pro if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 7 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

Gemini 2.5 Pro is clearly ahead on the BenchAlign aggregate, 56.66 to 43.1. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Gemini 2.5 Pro's sharpest advantage is in coding, where it averages 63.8 against 23.6. The single biggest benchmark swing on the page is SWE-bench Verified, 63.8% to 23.6%. GPT-4.1 mini does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Gemini 2.5 Pro is also the more expensive model on tokens at $1.25 input / $10.00 output per 1M tokens, versus $0.40 input / $1.60 output per 1M tokens for GPT-4.1 mini. That is roughly 6.3x on output cost alone.

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 Gemini 2.5 Pro and GPT-4.1 mini
CategoryGemini 2.5 ProΔGPT-4.1 mini
CodingGemini 2.5 Pro63.8Margin 40.2GPT-4.1 mini23.6
KnowledgeGemini 2.5 Pro27.4Margin 36.8GPT-4.1 mini64.2
MathGemini 2.5 Pro11.6Margin 7.1GPT-4.1 mini4.5
Inst. FollowingGemini 2.5 ProNot measuredMarginNo overlapGPT-4.1 mini88.5

Decisive benchmark drivers

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

More
A · Gemini 2.5 ProB · GPT-4.1 mini
  1. SWE-bench Verified

    Coding
    Source ↗
    A 63.8%B 23.6%
    Winner: Gemini 2.5 ProΔ 40.2
    SWE-bench Verified: Gemini 2.5 Pro scored 63.8%; GPT-4.1 mini scored 23.6%. Gemini 2.5 Pro wins this benchmark.
  2. GPQA

    Knowledge
    Source ↗
    A 83%B 64.2%
    Winner: Gemini 2.5 ProΔ 18.8
    GPQA: Gemini 2.5 Pro scored 83%; GPT-4.1 mini scored 64.2%. Gemini 2.5 Pro wins this benchmark.
  3. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 14.138%B 4.483%
    Winner: Gemini 2.5 ProΔ 9.7
    FrontierMath v2 (Tiers 1-3): Gemini 2.5 Pro scored 14.138%; GPT-4.1 mini scored 4.483%. Gemini 2.5 Pro wins this benchmark.

Operational comparison

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

MetricGemini 2.5 ProGPT-4.1 miniComparison
Input / output priceUSD per 1M tokensGemini 2.5 Pro$1.25 input / $10 outputGPT-4.1 mini$0.4 input / $1.6 outputGPT-4.1 mini has the lower combined listed price.
Generation speedtokens per secondGemini 2.5 Pro117 tok/sGPT-4.1 mini80 tok/sGemini 2.5 Pro has the higher measured throughput.
First-answer latencyseconds to first tokenGemini 2.5 Pro21.19 sGPT-4.1 mini0.76 sGPT-4.1 mini reaches the first token sooner.
Context windowmaximum listed tokensGemini 2.5 Pro1MGPT-4.1 mini1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGemini 2.5 ProGPT-4.1 miniResult
AA Agentic IndexSource 7.1%1.7%Gemini 2.5 Pro leads
τ²-bench resultsSource 54.1%52.9%Gemini 2.5 Pro leads
Gert LabsSource 42.01%Not comparable
GDPval-AASource 8.6%0.4%Gemini 2.5 Pro leads
GDPval-AASource 672508Gemini 2.5 Pro leads
CodingGemini 2.5 Pro wins
BenchmarkGemini 2.5 ProGPT-4.1 miniResult
SWE-bench VerifiedSource 63.8%23.6%Gemini 2.5 Pro leads
Vibe Code BenchSource 0.40%Not comparable
AA Coding IndexSource 33.3%20.2%Gemini 2.5 Pro leads
AA-SciCodeSource 42.8%40.4%Gemini 2.5 Pro leads
Reasoning
BenchmarkGemini 2.5 ProGPT-4.1 miniResult
AA-LCRSource 66.0%42.3%Gemini 2.5 Pro leads
CritPtSource 2.6%0.0%Gemini 2.5 Pro leads
KnowledgeGPT-4.1 mini wins
BenchmarkGemini 2.5 ProGPT-4.1 miniResult
GPQASource 83%64.2%Gemini 2.5 Pro leads
HLESource 18.8%Not comparable
Artificial Analysis Intelligence IndexSource 25.8%14.8%Gemini 2.5 Pro leads
AA-GPQA DiamondSource 84.4%66.4%Gemini 2.5 Pro leads
AA-HLESource 21.1%4.6%Gemini 2.5 Pro leads
AA-Omniscience IndexSource -14.3%-50.1%Gemini 2.5 Pro leads
AA-Omniscience AccuracySource 39.0%17.5%Gemini 2.5 Pro leads
AA-Omniscience Hallucination RateSource 87.4%82.0%GPT-4.1 mini leads
MMLUSource 87.5%Not comparable
MathGemini 2.5 Pro wins
BenchmarkGemini 2.5 ProGPT-4.1 miniResult
FrontierMath v2 (Tiers 1-3)Source 14.138%4.483%Gemini 2.5 Pro leads
FrontierMath v2 (Tier 4)Source 4.167%Not comparable
Multimodal
BenchmarkGemini 2.5 ProGPT-4.1 miniResult
AA-MMMU-ProSource 74.9%58.7%Gemini 2.5 Pro leads
Design Arena WebsiteSource 11971027Gemini 2.5 Pro leads
Inst. Following
BenchmarkGemini 2.5 ProGPT-4.1 miniResult
AA-IFBenchSource 48.7%38.3%Gemini 2.5 Pro leads
IFEvalSource 88.5%Not comparable
Frequently Asked Questions (4)

Which is better, Gemini 2.5 Pro or GPT-4.1 mini?

Gemini 2.5 Pro is ahead on BenchLM's BenchAlign leaderboard, 56.66 to 43.1. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 63.8% and 23.6%.

Which is better for knowledge tasks, Gemini 2.5 Pro or GPT-4.1 mini?

GPT-4.1 mini has the edge for knowledge tasks in this comparison, averaging 64.2 versus 27.4. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, Gemini 2.5 Pro or GPT-4.1 mini?

Gemini 2.5 Pro has the edge for coding in this comparison, averaging 63.8 versus 23.6. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Gemini 2.5 Pro or GPT-4.1 mini?

Gemini 2.5 Pro has the edge for math in this comparison, averaging 11.6 versus 4.5. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 24, 2026