Skip to main content

Model profile

GPT-4.1

OpenAIEstablishedReleased Apr 14, 2025
Data verified
Overall Score
51.11Public #108 of 200Verified #60 of 99
Arena Elo
1413
Eligible category ranks
2of 8
Price (1M tokens)
$2 in / $8 out
API pricing
Speed
108tok/s
Context
1M

Evidence coverage

20 of 323 tracked benchmarks are published. 7 are verified and 13 provisional. 7 of 8 categories are measured.

Updated July 22, 2026Methodology
Published / tracked
20 / 323
Verified
7
Provisional
13
Categories with evidence
7 / 8

Evidence by category

  • Agentic2 benchmarks
    Mixed evidence
  • Coding2 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge8 benchmarks
    Mixed evidence
  • Math2 benchmarks
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal2 benchmarks
    Reported
  • Inst. Following2 benchmarks
    Mixed evidence
ProprietaryNon-Reasoning
Confidence:
Low
base

GPT-4.1 ranks #108 out of 200 models on the public leaderboard with an overall score of 51.11/100. It also ranks #60 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

GPT-4.1 is a proprietary model with a 1M token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

GPT-4.1 sits inside the GPT-4.1 family alongside GPT-4.1 nano, GPT-4.1 mini. BenchLM links it directly to GPT-4o as the earlier related model in that lineage. This profile currently has 20 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Instruction Following (#20), while its weakest is Coding (#70). This performance profile makes it a well-rounded choice across a range of tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 50.8351.28

  1. Mercury 2
    Inception
    #10551.28
    Mercury 2 is #105 with a score of 51.28.
    Compare
  2. GLM-4.7-Flash
    Z.AI
    #10651.25
    GLM-4.7-Flash is #106 with a score of 51.25.
    Compare
  3. Grok 4.1 Fast
    xAI
    #10751.25
    Grok 4.1 Fast is #107 with a score of 51.25.
    Compare
  4. GPT-4.1Current model
    OpenAI
    #10851.11
    GPT-4.1 is #108 with a score of 51.11.
  5. Nemotron 3 Super 120B A12B
    NVIDIA
    #10950.97
    Nemotron 3 Super 120B A12B is #109 with a score of 50.97.
    Compare
  6. Step 3.7 Flash
    StepFun
    #11050.87
    Step 3.7 Flash is #110 with a score of 50.87.
    Compare
  7. Gemini 3.1 Flash-Lite
    Google
    #11150.83
    Gemini 3.1 Flash-Lite is #111 with a score of 50.83.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Inst. Following37%
    Eligible cohort rank #20 of 31Category score 71.4
  2. Coding43%
    Eligible cohort rank #70 of 122Category score 49.2

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank Not rankedWeight 22%2 benchmarksMixed sources65.0
CodingRank #70 of 122Percentile 43rdWeight 20%2 benchmarksMixed sources49.2
ReasoningRank Not rankedWeight 17%2 benchmarksReported80.9
KnowledgeRank Not rankedWeight 12%8 benchmarksMixed sources55.0
MathRank Not rankedWeight 5%2 benchmarksVerified28.3
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%2 benchmarksReported73.2
Inst. FollowingRank #20 of 31Percentile 37thWeight 5%2 benchmarksMixed sources71.4

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1413Not availableNot available

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic2 benchmarks
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

47.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

25.65%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
Coding2 benchmarks
SWE-bench VerifiedProvider exact

Software Engineering Benchmark Verified

54.6%Weighted 16%
Source: OpenAI: Introducing GPT-4.1 in the APIProvenance: Provider exact
AA-SciCodeReported

Artificial Analysis SciCode

38.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

61.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

0.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge8 benchmarks
GPQAProvider exact

Graduate-Level Google-Proof Q&A

66.3%Weighted 7%
Source: OpenAI: Introducing GPT-4.1 in the APIProvenance: Provider exact
MMLUProvider exact

Massive Multitask Language Understanding

90.2%Display only
Source: OpenAI: Introducing GPT-4.1 in the APIProvenance: Provider exact
Artificial Analysis Intelligence IndexReported
19.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

66.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

4.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-36.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

24.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

79.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math2 benchmarks
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

5.517%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 5.517% for gpt-4.1-2025-04-14. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath v2 (Tier 4)Benchmark exact

FrontierMath v2 Tier 4

0.000%Weighted 10%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tier 4 at 0% for gpt-4.1-2025-04-14. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
Multimodal2 benchmarks
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

61.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Design Arena WebsiteReported

Design Arena Website Elo

1068Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following2 benchmarks
IFEvalProvider exact

Instruction-Following Eval

87.4%Weighted 35%
Source: OpenAI: Introducing GPT-4.1 in the APIProvenance: Provider exact
AA-IFBenchReported

Artificial Analysis IFBench

43.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

GPT-4.1 Family

Base entry

Related Earlier Model

GPT-4o

Frequently Asked Questions

How does GPT-4.1 perform overall in AI benchmarks?

GPT-4.1 has 20 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is GPT-4.1 good for knowledge and understanding?

GPT-4.1 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is GPT-4.1 good for coding and programming?

GPT-4.1 ranks #70 out of 122 models in coding and programming benchmarks with an average score of 49.2. There are stronger options in this category.

Is GPT-4.1 good for mathematics?

GPT-4.1 has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is GPT-4.1 good for reasoning and logic?

GPT-4.1 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is GPT-4.1 good for agentic tool use and computer tasks?

GPT-4.1 has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is GPT-4.1 good for multimodal and grounded tasks?

GPT-4.1 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is GPT-4.1 good for instruction following?

GPT-4.1 ranks #20 out of 31 models in instruction following benchmarks with an average score of 71.4. There are stronger options in this category.

Which sibling models are related to GPT-4.1?

GPT-4.1 belongs to the GPT-4.1 family. Related variants on BenchLM include GPT-4.1 nano, GPT-4.1 mini.

Does GPT-4.1 have full benchmark coverage on BenchLM?

Not yet. GPT-4.1 currently has 20 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of GPT-4.1?

GPT-4.1 has a published context window of 1M, which determines how much text it can process in a single interaction.

Last updated: July 22, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.